You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/09/02 04:57:08 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@8ca8f24d54d65be552448e5368d879710930711b)
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 5bf93521a deploying docs (apache/tvm@8ca8f24d54d65be552448e5368d879710930711b)
5bf93521a is described below
commit 5bf93521a578a18024ffd7d548eef56dc6fa1de3
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Sep 2 04:57:01 2022 +0000
deploying docs (apache/tvm@8ca8f24d54d65be552448e5368d879710930711b)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2713 +++++++++++++-------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 127 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 13 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 24 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 55 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 39 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2713 +++++++++++++-------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 127 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
.../api/doxygen/c__backend__api_8h_source.html | 4 +-
.../api/doxygen/c__runtime__api_8h_source.html | 4 +-
...stvm_1_1meta__schedule_1_1Database-members.html | 10 +-
.../classtvm_1_1meta__schedule_1_1Database.html | 80 +-
..._1_1meta__schedule_1_1Database__coll__graph.svg | 124 +-
...1meta__schedule_1_1Database__inherit__graph.svg | 86 +-
.../classtvm_1_1tir_1_1DeclBuffer-members.html | 9 +-
.../api/doxygen/classtvm_1_1tir_1_1DeclBuffer.html | 24 +-
.../classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg | 120 +-
...asstvm_1_1tir_1_1DeclBuffer__inherit__graph.svg | 90 +-
.../classtvm_1_1tir_1_1Stmt__inherit__graph.svg | 20 +-
.../api/doxygen/compilation__config_8h_source.html | 2 +-
docs/reference/api/doxygen/database_8h_source.html | 2 +-
.../api/doxygen/detail_2extern_8h_source.html | 2 +-
.../api/doxygen/device__api_8h_source.html | 2 +-
docs/reference/api/doxygen/functions_func_o.html | 17 +-
docs/reference/api/doxygen/functions_func_s.html | 6 +-
docs/reference/api/doxygen/functions_func_t.html | 9 +-
docs/reference/api/doxygen/functions_func_u.html | 5 +-
docs/reference/api/doxygen/functions_func_v.html | 2 +-
docs/reference/api/doxygen/functions_m.html | 2 +-
docs/reference/api/doxygen/functions_o.html | 15 +-
docs/reference/api/doxygen/functions_s.html | 8 +-
docs/reference/api/doxygen/functions_t.html | 7 +-
docs/reference/api/doxygen/functions_u.html | 5 +-
docs/reference/api/doxygen/functions_v.html | 6 +-
.../reference/api/doxygen/profiling_8h_source.html | 4 +-
docs/reference/api/doxygen/search/all_10.js | 1 +
docs/reference/api/doxygen/search/all_11.js | 2 +-
docs/reference/api/doxygen/search/all_13.js | 2 +-
docs/reference/api/doxygen/search/all_14.js | 12 +-
docs/reference/api/doxygen/search/all_15.js | 8 +-
docs/reference/api/doxygen/search/all_16.js | 5 +-
docs/reference/api/doxygen/search/all_17.js | 2 +-
docs/reference/api/doxygen/search/all_18.js | 2 +-
docs/reference/api/doxygen/search/all_d.js | 2 +-
docs/reference/api/doxygen/search/all_e.js | 2 +-
docs/reference/api/doxygen/search/functions_10.js | 2 +-
docs/reference/api/doxygen/search/functions_12.js | 2 +-
docs/reference/api/doxygen/search/functions_13.js | 10 +-
docs/reference/api/doxygen/search/functions_14.js | 2 +-
docs/reference/api/doxygen/search/functions_15.js | 5 +-
docs/reference/api/doxygen/search/functions_16.js | 2 +-
docs/reference/api/doxygen/search/functions_c.js | 2 +-
docs/reference/api/doxygen/search/functions_f.js | 1 +
docs/reference/api/doxygen/search/typedefs_e.js | 2 +-
.../api/doxygen/serializer_8h_source.html | 2 +-
docs/reference/api/doxygen/stmt_8h_source.html | 322 +--
.../api/doxygen/stmt__functor_8h_source.html | 16 +-
.../api/doxygen/target__kind_8h_source.html | 2 +-
.../api/doxygen/te_2schedule_8h_source.html | 2 +-
.../api/doxygen/tir_2analysis_8h_source.html | 2 +-
docs/reference/api/doxygen/tir_2op_8h_source.html | 4 +-
.../doxygen/tir_2schedule_2schedule_8h_source.html | 6 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 8 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
175 files changed, 5225 insertions(+), 3179 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 0a7b4a469..37c02c752 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.009 seconds)
+ **Total running time of the script:** ( 1 minutes 6.695 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 269b59011..97810cea6 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip07db3c73-3db9-48d3-8230-c7f829dd6103 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2f5c0f38-d1e0-45cc-b314-3bd3b27fc4ff from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index db6305ee4..9e687095a 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 56.3MB/s]
28%|##8 | 11.7M/41.5M [00:00<00:00, 47.4MB/s]
39%|###9 | 16.3M/41.5M [00:00<00:00, 29.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 35.5MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.9MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 52.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 46.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 42.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 44.5MB/s]
45%|####4 | 18.6M/41.5M [00:00<00:00, 42.5MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 37.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.0MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 39.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 41.3MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 7ec35d41b..f650cd156 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
41%|#### | 18.1M/44.7M [00:00<00:00, 190MB/s]
92%|#########2| 41.2M/44.7M [00:00<00:00, 221MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 221MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
38%|###8 | 17.0M/44.7M [00:00<00:00, 178MB/s]
76%|#######6 | 34.0M/44.7M [00:00<00:00, 174MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 188MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index 65ed28d07..af723c105 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.757 seconds)
+ **Total running time of the script:** ( 1 minutes 8.813 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 8d692bbf2..ee8e26a79 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:08.355** total execution time for **how_to_compile_models** files:
+**05:24.015** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:04.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:08.813 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.757 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.695 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.478 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:41.964 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:30.046 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.766 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.569 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.009 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.986 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.036 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.809 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.295 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.362 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.632 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 1dbbe16aa..f45f0494e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.5967 16.3693 17.2798 16.0005 0.5185
+ 16.4733 16.3969 17.3753 16.1531 0.3131
diff --git a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
index 38fae9353..fb8b12567 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 3.21M/170M [00:00<00:05, 33.7MB/s]
4%|3 | 6.50M/170M [00:00<00:05, 34.1MB/s]
14%|#4 | 23.9M/170M [00:00<00:01, 102MB/s]
28%|##8 | 47.8M/170M [00:00<00:00, 161MB/s]
43%|####2 | 72.5M/170M [00:00<00:00, 196MB/s]
57%|#####7 | 97.3M/170M [00:00<00:00, 218MB/s]
70%|####### | 119M/170M [00:00<00:00, 222MB/s]
84%|########3 | 142M/170M [00:00<00:00, 228MB/s]
97%|#########6| 164M/170M [00:00<00:00, 228MB/s]
100%|##########| 170M/170M [00:00<00:00, 192MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|3 | 5.12M/170M [00:00<00:03, 53.7MB/s]
6%|6 | 10.2M/170M [00:00<00:04, 36.3MB/s]
8%|8 | 14.0M/170M [00:00<00:04, 34.5MB/s]
11%|#1 | 19.3M/170M [00:00<00:03, 41.3MB/s]
15%|#5 | 26.2M/170M [00:00<00:03, 49.5MB/s]
19%|#9 | 32.8M/170M [00:00<00:02, 55.5MB/s]
24%|##3 | 40.6M/170M [00:00<00:02, 63.6MB/s]
28%|##7 | 46.9M/170M [00:00<00:02, 60.2MB/s]
31%|###1 | 52.8M/170M [00:01<00:02, 58.7MB/s]
34%|###4 | 58.5M/170M [00:01<00:03, 36.4MB/s]
37%|###7 | 63.0M/170M [00:01<00:02, 37.4MB/s]
40%|###9 | 67.4M/170M [00:01<00:02, 37.3MB/s]
42%|####2 | 71.4M/170M [00:01<00:02, 37.6MB/s]
44%|####4 | 75.4M/170M [00:01<00:02, 34.4MB/s]
46%|####6 | 79.0M/170M [00:02<00:02, 32.1MB/s]
48%|####8 | 82.2M/170M [00:02<00:02, 31.1MB/s]
51%|##### | 85.8M/170M [00:02<00:02, 32.6MB/
s]
52%|#####2 | 89.0M/170M [00:02<00:02, 28.7MB/s]
54%|#####4 | 91.9M/170M [00:02<00:03, 26.6MB/s]
56%|#####5 | 94.8M/170M [00:02<00:02, 27.0MB/s]
58%|#####7 | 97.9M/170M [00:02<00:02, 28.5MB/s]
59%|#####9 | 101M/170M [00:02<00:02, 28.7MB/s]
61%|###### | 104M/170M [00:02<00:02, 28.8MB/s]
63%|######2 | 106M/170M [00:03<00:02, 28.8MB/s]
64%|######4 | 109M/170M [00:03<00:02, 29.3MB/s]
66%|######6 | 112M/170M [00:03<00:02, 26.4MB/s]
68%|######7 | 115M/170M [00:03<00:02, 28.0MB/s]
70%|######9 | 119M/170M [00:03<00:01, 30.2MB/s]
72%|#######1 | 122M/170M [00:03<00:01, 30.3MB/s]
73%|#######3 | 125M/170M [00:03<00:01, 26.1MB/s]
75%|#######5 | 128M/170M [00:03<00:01, 26.9MB/s]
78%|#######7 | 132M/170M [00:03<00:01, 31.4MB/s]
80%|#######9 | 135M/170M [00:04<00:01, 29.7MB/s]
82%|########1 | 139M/170M [00:04<00:01, 32.4MB/s]
84%|########3 | 142M/170M [00:04<00:00, 33.0MB/s]
86%|########6 | 146M/170M [00:04<00:00, 34.9MB/s]
88%|########8 | 150M/170M [00:04<00:00, 36.2MB/s]
91%|######### | 154M/170M [00:04<00:00, 37.3MB/s]
93%|#########2| 158M/170M [00:04<00:00, 36.8MB/s]
95%|#########4| 161M/170M [00:04<00:00, 33.8MB/s]
98%|#########7| 166M/170M [00:04<00:00, 37.4MB/s]
100%|#########9| 170M/170M [00:05<00:00, 38.6MB/s]
100%|##########| 170M/170M [00:05<00:00, 35.4MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 7.503 seconds)
+ **Total running time of the script:** ( 3 minutes 12.875 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_object_detection_pytorch.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
index c982c661c..0eb4447a9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 167MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
8%|7 | 1.06M/13.6M [00:00<00:01, 11.0MB/s]
22%|##2 | 3.02M/13.6M [00:00<00:00, 16.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 52.7MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3388 90.2751 92.1478 90.1221 0.2583
+ 90.4171 90.3343 95.6119 90.1207 0.5643
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.344 seconds)
+ **Total running time of the script:** ( 1 minutes 13.723 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
index 3da360e4c..77bca16b5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.9834 120.9221 122.9194 119.5148 0.7500
+ 122.1707 122.0668 129.6572 120.9341 0.8749
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 0.485 seconds)
+ **Total running time of the script:** ( 2 minutes 5.507 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized_tflite.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
index 5d2dea90a..eeb82a7e9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.662 seconds)
+ **Total running time of the script:** ( 1 minutes 36.686 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_quantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
index 813a642a1..e716b4ae0 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5903/132723 [00:00<00:02, 59023.16KB/s]
10%|9 | 13168/132723 [00:00<00:01, 67033.25KB/s]
15%|#4 | 19872/132723 [00:00<00:01, 56776.99KB/s]
20%|## | 27208/132723 [00:00<00:01, 62669.29KB/s]
25%|##5 | 33635/132723 [00:00<00:01, 59599.78KB/s]
31%|### | 40880/132723 [00:00<00:01, 63610.58KB/s]
36%|###6 | 48253/132723 [00:00<00:01, 66729.45KB/s]
42%|####1 | 55646/132723 [00:00<00:01, 68929.97KB/s]
47%|####7 | 62945/132723 [00:00<00:00, 70161.76KB/s]
53%|#####2 | 70342/132723 [00:01<00:00, 71313.48KB/s]
59%|#####8 | 77747/132723 [00:01<00:00, 72133.14KB/s]
64%|######4 | 85137/132723 [00:01<00:00, 72663.22KB/s]
70%|######9 | 92531/132723 [00:01<00:00, 73043.23KB/s]
75%|#######5 | 99850/132723 [00:01<00:00, 50637.73KB/s]
81%|######## | 107221/132723 [00:01<00:00, 55927.99KB/s]
86%|########6
| 114680/132723 [00:01<00:00, 55044.71KB/s]
92%|#########1| 121797/132723 [00:01<00:00, 58958.44KB/s]
97%|#########7| 129237/132723 [00:02<00:00, 62931.15KB/s]
100%|##########| 132723/132723 [00:02<00:00, 63467.64KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5191/132723 [00:00<00:02, 51904.11KB/s]
10%|9 | 12779/132723 [00:00<00:01, 65992.24KB/s]
15%|#5 | 20402/132723 [00:00<00:01, 70663.44KB/s]
21%|##1 | 28027/132723 [00:00<00:01, 72862.01KB/s]
27%|##6 | 35737/132723 [00:00<00:01, 74385.74KB/s]
33%|###2 | 43459/132723 [00:00<00:01, 75344.59KB/s]
39%|###8 | 51173/132723 [00:00<00:01, 75927.36KB/s]
44%|####4 | 58912/132723 [00:00<00:00, 76391.51KB/s]
50%|##### | 66598/132723 [00:00<00:00, 76536.09KB/s]
56%|#####6 | 74344/132723 [00:01<00:00, 76818.55KB/s]
62%|######1 | 82048/132723 [00:01<00:00, 76884.60KB/s]
68%|######7 | 89737/132723 [00:01<00:00, 76874.39KB/s]
73%|#######3 | 97472/132723 [00:01<00:00, 77016.75KB/s]
79%|#######9 | 105174/132723 [00:01<00:00, 76906.11KB/s]
85%|########5 | 112877/132723 [00:01<00:00, 76940.07KB/s]
91%|#########
| 120572/132723 [00:01<00:00, 76613.46KB/s]
97%|#########6| 128283/132723 [00:01<00:00, 76753.32KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75419.83KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 44.121 seconds)
+ **Total running time of the script:** ( 2 minutes 46.619 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_ssd_gluoncv.py:
diff --git a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
index 5cdc403d9..38b467176 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:58.244** total execution time for **how_to_deploy_models** files:
+**12:15.027** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:07.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:12.875 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:44.121 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:46.619 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:00.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:05.507 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.662 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.686 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:12.344 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.723 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.550 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:32.192 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.563 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.926 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.491 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index aaa030a82..a78f23fb6 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipecaa6d31-8fb0-4d0e-b2f7-b72dfe2d3677 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip110168ce-5ca5-4266-bd09-0d7497c4930b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index ca1ec2ae8..2b619aae1 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:43.379** total execution time for **how_to_extend_tvm** files:
+**00:44.688** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:40.094 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:41.250 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.290 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.389 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.986 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.041 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 643247322..9acc13ed2 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7160us [7160us] (46.63%; 46.63%)
- FoldScaleAxis: 8195us [8us] (53.37%; 53.37%)
- FoldConstant: 8187us [1622us] (53.32%; 99.90%)
- InferType: 6565us [6565us] (42.76%; 80.19%)
+ InferType: 7696us [7696us] (46.82%; 46.82%)
+ FoldScaleAxis: 8741us [8us] (53.18%; 53.18%)
+ FoldConstant: 8733us [1815us] (53.13%; 99.91%)
+ InferType: 6918us [6918us] (42.09%; 79.22%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6646us [6646us] (44.92%; 44.92%)
- FoldScaleAxis: 8149us [7us] (55.08%; 55.08%)
- FoldConstant: 8142us [1657us] (55.03%; 99.92%)
- InferType: 6485us [6485us] (43.83%; 79.65%)
+ InferType: 7161us [7161us] (45.68%; 45.68%)
+ FoldScaleAxis: 8516us [7us] (54.32%; 54.32%)
+ FoldConstant: 8509us [1768us] (54.27%; 99.91%)
+ InferType: 6741us [6741us] (43.00%; 79.22%)
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
index 9fa5b6d02..562097f9a 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 37.159966 ms
+ Convolution: 54.219203 ms
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
index df79759a9..9cbcf31be 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 7.747671 ms
+ conv2d with tensor core: 9.059836 ms
diff --git a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
index cf034b8f2..cae5cd35d 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019256
- Baseline: 3.376091
+ Numpy running time: 0.019549
+ Baseline: 3.513594
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.324201
+ Opt1: 0.332782
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.350502
+ Opt2: 0.347643
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120167
+ Opt3: 0.138471
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110161
+ Opt4: 0.111052
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111205
+ Opt5: 0.113193
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147490
+ Opt6: 0.149446
diff --git a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
index 57fe4d69a..c20d5de26 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.066** total execution time for **how_to_optimize_operators** files:
+**00:36.096** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.798 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.674 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.246 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.331 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.092 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 5b191cc1f..4b891f8c8 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:15.886** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:27.042** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:24.362 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:32.304 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:25.085 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:26.596 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:48.331 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:48.952 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.752 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:20.448 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.286 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.476 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.070 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.267 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 7967cb3d8..c883873f0 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,12 +240,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -253,470 +253,938 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 17), 81)) && (floormod((threadIdx.x_1 + 17), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (floormod((threadIdx.x_1 + 4), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 21), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 25), 81)) && (floormod((threadIdx.x_1 + 25), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 46), 81)) && (floormod((threadIdx.x_1 + 46), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 16), 81)) && (floormod((threadIdx.x_1 + 16), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 33), 81)) && (floormod((threadIdx.x_1 + 33), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2058), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 33), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2254), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (floormod((threadIdx.x_1 + 3), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 20), 81)) && (floormod((threadIdx.x_1 + 20), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2450), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*73728) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 294), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 490), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 686), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 882), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1078), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 214), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1274), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 122), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1470), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 10)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1666)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1666), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 226), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1862)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1862), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 134), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2058)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2058), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 14)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2254)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2254), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 238), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2450)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2450), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 146), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2646)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2646), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 18)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2842)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2842), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 250), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3038)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3038), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 158), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3234)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3234), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 22)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3430)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3430), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 262), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3626)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3626), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 170), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3822)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3822), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 26)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4018)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4018), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 274), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4214)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4214), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 182), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4410)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4410), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 30)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 2), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4606)] = kernel[(((((blockIdx.x*73728) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 286), 288), 3)*3)) + (threadIdx.x_2 + 1)) + 69120)]
+ }
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 291)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 294)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 300)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 303)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 309)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 312)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 318)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 321)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 327)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 330)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 336)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 339)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 345)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 348)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 354)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 357)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 363)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 366)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 372)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 375)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 381)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 384)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 390)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 393)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 399)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 402)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 408)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 411)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 417)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 420)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 426)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 429)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 147)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 435)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 150)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 438)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 156)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 444)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 159)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 447)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 165)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 453)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 168)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 456)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 174)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 462)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 177)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 465)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 183)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 471)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 186)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 474)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 192)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 480)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 195)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 483)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 201)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 489)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 204)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 492)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 210)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 498)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 213)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 501)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 219)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 507)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 222)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 510)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 516)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 519)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 237)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 525)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 240)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 528)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 246)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 534)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 249)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 537)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 255)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 543)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 258)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 546)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 264)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 552)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 267)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 555)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 273)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 561)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 276)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 564)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 282)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 570)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 285)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 573)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 864)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 867)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 870)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 873)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 876)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 879)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 882)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 597)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 885)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 600)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 888)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 891)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 606)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 894)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 609)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 897)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 612)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 900)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 615)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 903)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 618)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 906)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 621)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 909)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 624)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 912)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 627)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 915)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 630)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 918)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 633)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 921)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 636)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 924)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 639)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 927)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 642)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 930)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 645)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 933)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 648)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 936)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 651)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 939)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 654)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 942)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 657)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 945)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 660)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 948)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 663)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 951)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 666)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 954)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 669)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 957)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 672)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 960)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 675)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 963)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 678)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 966)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 681)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 969)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 684)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 972)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 687)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 975)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 690)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 978)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 693)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 981)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 696)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 984)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 699)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 987)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 702)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 990)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 705)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 993)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 708)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 996)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 711)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 999)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 714)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1002)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 717)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1005)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 720)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1008)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 723)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1011)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 726)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1014)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 729)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1017)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 732)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1020)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 735)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1023)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 738)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1026)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 741)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1029)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 744)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1032)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 747)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1035)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 750)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1038)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 753)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1041)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 756)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1044)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 759)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1047)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 762)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1050)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 765)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1053)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1056)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1059)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1062)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1065)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1068)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1071)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1074)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1077)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1080)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1083)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1086)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1089)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1092)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1095)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1098)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 816)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 819)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 822)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1110)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 825)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1113)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 828)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1116)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 831)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 834)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1122)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 837)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1125)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 840)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1128)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 843)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1131)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 846)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1134)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 849)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1137)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 852)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1140)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 855)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1143)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 858)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1146)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 861)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1149)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1152)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1440)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1155)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1443)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1158)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1446)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1161)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1449)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1164)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1452)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1167)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1455)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1170)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1458)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1173)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1461)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1176)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1464)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1179)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1467)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1182)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1470)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1185)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1473)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1188)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1476)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1191)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1479)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1194)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1482)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1197)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1485)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1200)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1488)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1203)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1491)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1206)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1494)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1209)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1497)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1212)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1500)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1215)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1503)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1218)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1506)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1221)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1509)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1224)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1512)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1227)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1515)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1230)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1518)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1233)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1521)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1236)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1524)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1239)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1527)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1242)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1530)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1245)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1533)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1248)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1251)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1254)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1257)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1260)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1263)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1266)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1269)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1272)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1275)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1278)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1281)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1284)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1287)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1290)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1293)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1296)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1584)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1299)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1587)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1302)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1590)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1305)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1593)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1308)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1596)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1311)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1599)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1314)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1602)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1317)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1605)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1320)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1608)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1323)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1611)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1326)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1614)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1329)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1617)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1332)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1620)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1335)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1623)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1338)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1626)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1341)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1629)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1344)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1632)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1347)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1635)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1350)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1638)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1353)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1641)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1356)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1644)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1359)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1647)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1362)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1650)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1365)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1653)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1368)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1656)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1371)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1659)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1374)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1662)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1377)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1665)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1380)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1668)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1383)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1671)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1386)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1674)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1389)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1677)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1392)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1680)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1395)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1683)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1398)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1686)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1401)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1689)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1404)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1692)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1407)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1695)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1410)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1698)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1413)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1701)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1416)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1704)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1419)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1707)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1422)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1710)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1425)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1713)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1428)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1716)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1431)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1719)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1434)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1722)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1437)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1725)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1728)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2016)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1731)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2019)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1734)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2022)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1737)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2025)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1740)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2028)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1743)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2031)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1746)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2034)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1749)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2037)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1752)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2040)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1755)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2043)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1758)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2046)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1761)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2049)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1764)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2052)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1767)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2055)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1770)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2058)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1773)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2061)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1776)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2064)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1779)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2067)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1782)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2070)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1785)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2073)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1788)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2076)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1791)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2079)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1794)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2082)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1797)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2085)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1800)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2088)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1803)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2091)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1806)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2094)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1809)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2097)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1812)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1815)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1818)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1821)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2109)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1824)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2112)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1827)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2115)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1830)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2118)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1833)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2121)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1836)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2124)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1839)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2127)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1842)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2130)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1845)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2133)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1848)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2136)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1851)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2139)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1854)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2142)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1857)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2145)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1860)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2148)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1863)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2151)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1866)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2154)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1869)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2157)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1872)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2160)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1875)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2163)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1878)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2166)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1881)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2169)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1884)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2172)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1887)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2175)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1890)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2178)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1893)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2181)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1896)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2184)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1899)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2187)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1902)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2190)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1905)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1908)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1911)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2199)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1914)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2202)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1917)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2205)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1920)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2208)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1923)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2211)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1926)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2214)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1929)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2217)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1932)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2220)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1935)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2223)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1938)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2226)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1941)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2229)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1944)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2232)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1947)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2235)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1950)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2238)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1953)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2241)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1956)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2244)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1959)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2247)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1962)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2250)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1965)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2253)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1968)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2256)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1971)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2259)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1974)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2262)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1977)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2265)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1980)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2268)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1983)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2271)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1986)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2274)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1989)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2277)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1992)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2280)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1995)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2283)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1998)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2286)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2001)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2289)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2004)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2292)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2007)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2295)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2010)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2298)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2013)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2301)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 8) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*392)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*8)) + i1.inner)]), 0f32)
}
}
}
@@ -771,7 +1239,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.358 ms
+ Execution time of this operator: 0.327 ms
@@ -819,21 +1287,21 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
@@ -841,14 +1309,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -868,14 +1336,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -893,10 +1361,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -905,418 +1373,861 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((9 <= ((((int)threadIdx.x) + 17) % 81)) && (((((int)threadIdx.x) + 17) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((9 <= ((((int)threadIdx.x) + 4) % 81)) && (((((int)threadIdx.x) + 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 81) * 49)) + ((((((int)threadIdx.x) + 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((9 <= ((((int)threadIdx.x) + 25) % 81)) && (((((int)threadIdx.x) + 25) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + ((((((int)threadIdx.x) + 25) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((9 <= ((((int)threadIdx.x) + 46) % 81)) && (((((int)threadIdx.x) + 46) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 81) * 49)) + ((((((int)threadIdx.x) + 46) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((9 <= ((((int)threadIdx.x) + 16) % 81)) && (((((int)threadIdx.x) + 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + ((((((int)threadIdx.x) + 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((9 <= ((((int)threadIdx.x) + 33) % 81)) && (((((int)threadIdx.x) + 33) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2058) / 81) * 49)) + ((((((int)threadIdx.x) + 33) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2254) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((9 <= ((((int)threadIdx.x) + 3) % 81)) && (((((int)threadIdx.x) + 3) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + ((((((int)threadIdx.x) + 3) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((9 <= ((((int)threadIdx.x) + 20) % 81)) && (((((int)threadIdx.x) + 20) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2450) / 81) * 49)) + ((((((int)threadIdx.x) + 20) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 98) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 202) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 110) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 18)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 116) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 214) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 122) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 30)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 226) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 134) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 42)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 140) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 238) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2450)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2450) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 146) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2646)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2646) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 54)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2842)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2842) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 250) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
+ kernel_shared[(((int)threadIdx.x) + 3038)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3038) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 158) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3234)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3234) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 66)];
+ kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 164) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3430)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3430) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 262) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 3626)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3626) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 170) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3822)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3822) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 78)];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4018)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4018) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 274) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
+ kernel_shared[(((int)threadIdx.x) + 4214)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4214) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 182) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4410)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4410) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 90)];
+ kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 2) {
+ kernel_shared[(((int)threadIdx.x) + 4606)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 286) / 3) * 3)) + ((int)threadIdx.x)) + 69121)];
}
+ __syncthreads();
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 288)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 291)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 294)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 297)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 300)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 303)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 306)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 309)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 312)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 315)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 318)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 321)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 324)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 327)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 330)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 333)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 336)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 339)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 342)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 345)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 348)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 351)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 354)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 357)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 360)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 363)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 366)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 369)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 372)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 375)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 378)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 381)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 384)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 387)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 390)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 393)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 396)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 399)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 402)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 405)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 408)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 411)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 414)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 417)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 420)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 423)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 426)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 429)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 432)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 147)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 435)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 150)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 438)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 153)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 441)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 156)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 444)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 159)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 447)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 162)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 450)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 165)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 453)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 168)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 456)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 171)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 459)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 174)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 462)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 177)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 465)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 180)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 468)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 183)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 471)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 186)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 474)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 189)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 477)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 480)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 195)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 483)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 198)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 486)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 201)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 489)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 204)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 492)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 207)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 495)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 210)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 498)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 213)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 501)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 216)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 504)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 219)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 507)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 222)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 510)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 513)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 516)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 519)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 234)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 522)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 237)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 525)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 240)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 528)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 243)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 531)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 246)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 534)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 249)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 537)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 252)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 540)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 255)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 543)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 258)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 546)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 261)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 549)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 264)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 552)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 267)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 555)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 270)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 558)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 273)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 561)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 276)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 564)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 279)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 567)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 282)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 570)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 285)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 573)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 864)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 867)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 870)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 873)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 876)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 879)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 882)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 597)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 885)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 600)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 888)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 891)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 606)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 894)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 609)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 897)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 612)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 900)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 615)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 903)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 618)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 906)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 621)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 909)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 624)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 912)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 627)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 915)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 630)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 918)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 633)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 921)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 636)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 924)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 639)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 927)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 642)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 930)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 645)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 933)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 648)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 936)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 651)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 939)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 654)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 942)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 657)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 945)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 660)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 948)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 663)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 951)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 666)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 954)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 669)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 957)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 672)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 960)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 675)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 963)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 678)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 966)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 681)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 969)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 684)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 972)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 687)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 975)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 690)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 978)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 693)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 981)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 696)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 984)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 699)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 987)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 702)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 990)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 705)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 993)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 708)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 996)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 711)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 999)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 714)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1002)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 717)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1005)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 720)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1008)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 723)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1011)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 726)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1014)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 729)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1017)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 732)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1020)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 735)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1023)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 738)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1026)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 741)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1029)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 744)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1032)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 747)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1035)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 750)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1038)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 753)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1041)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 756)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1044)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 759)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1047)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 762)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1050)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 765)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1053)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 768)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1056)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 771)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1059)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 774)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1062)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 777)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1065)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 780)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1068)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 783)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1071)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 786)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1074)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 789)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1077)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 792)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1080)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 795)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1083)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 798)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1086)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 801)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1089)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 804)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1092)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 807)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1095)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 810)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1098)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 813)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 816)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 819)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 822)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1110)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 825)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1113)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 828)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1116)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 831)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 834)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1122)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 837)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1125)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 840)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1128)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 843)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1131)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 846)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1134)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 849)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1137)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 852)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1140)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 855)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1143)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 858)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1146)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 861)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1149)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1152)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1440)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1155)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1443)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1158)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1446)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1161)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1449)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1164)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1452)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1167)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1455)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1170)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1458)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1173)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1461)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1176)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1464)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1179)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1467)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1182)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1470)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1185)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1473)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1188)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1476)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1191)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1479)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1194)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1482)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1197)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1485)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1200)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1488)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1203)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1491)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1206)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1494)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1209)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1497)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1212)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1500)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1215)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1503)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1218)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1506)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1221)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1509)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1224)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1512)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1227)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1515)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1230)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1518)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1233)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1521)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1236)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1524)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1239)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1527)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1242)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1530)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1245)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1533)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1248)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1251)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1254)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1257)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1260)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1263)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1266)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1269)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1272)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1275)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1278)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1281)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1284)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1287)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1290)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1293)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1296)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1299)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1302)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1590)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1305)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1593)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1308)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1596)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1311)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1599)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1314)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1602)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1317)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1605)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1320)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1608)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1323)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1611)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1326)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1614)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1329)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1617)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1332)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1620)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1335)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1623)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1338)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1626)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1341)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1629)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1344)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1632)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1347)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1635)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1350)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1638)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1353)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1641)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1356)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1644)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1359)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1647)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1362)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1650)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1365)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1653)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1368)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1656)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1371)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1659)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1374)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1662)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1377)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1665)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1380)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1668)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1383)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1671)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1386)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1674)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1389)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1677)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1392)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1680)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1395)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1683)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1398)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1686)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1401)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1689)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1404)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1692)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1407)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1695)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1410)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1698)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1413)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1701)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1416)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1704)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1419)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1707)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1422)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1710)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1425)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1713)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1428)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1716)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1431)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1719)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1434)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1722)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1437)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1725)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1728)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2016)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1731)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2019)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1734)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2022)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1737)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2025)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1740)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2028)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1743)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2031)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1746)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2034)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1749)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2037)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1752)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2040)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1755)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2043)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1758)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2046)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1761)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2049)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1764)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2052)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1767)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2055)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1770)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2058)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1773)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2061)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1776)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2064)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1779)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2067)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1782)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2070)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1785)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2073)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1788)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2076)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1791)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2079)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1794)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2082)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1797)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2085)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1800)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2088)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1803)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2091)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1806)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2094)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1809)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2097)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1812)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1815)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1818)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1821)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2109)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1824)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2112)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1827)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2115)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1830)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2118)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1833)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2121)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1836)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2124)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1839)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2127)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1842)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2130)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1845)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2133)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1848)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2136)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1851)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2139)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1854)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2142)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1857)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2145)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1860)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2148)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1863)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2151)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1866)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2154)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1869)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2157)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1872)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2160)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1875)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2163)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1878)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2166)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1881)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2169)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1884)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2172)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1887)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2175)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1890)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2178)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1893)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2181)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1896)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2184)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1899)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2187)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1902)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2190)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1905)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1908)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1911)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2199)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1914)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2202)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1917)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2205)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1920)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2208)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1923)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2211)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1926)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2214)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1929)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2217)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1932)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2220)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1935)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2223)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1938)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2226)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1941)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2229)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1944)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2232)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1947)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2235)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1950)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2238)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1953)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2241)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1956)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2244)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1959)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2247)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1962)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2250)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1965)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2253)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1968)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2256)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1971)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2259)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1974)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2262)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1977)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2265)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1980)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2268)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1983)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2271)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1986)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2274)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1989)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2277)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1992)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2280)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1995)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2283)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1998)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2286)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2001)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2289)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2004)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2292)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2007)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2295)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2010)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2298)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2013)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2301)]));
+ }
+ }
+ for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 8)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1378,7 +2289,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 24.362 seconds)
+ **Total running time of the script:** ( 3 minutes 32.304 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
index 750346b67..2591d097f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.9072 9.9166 9.9443 9.8609 0.0347
+ 10.1722 10.1849 10.2133 10.1185 0.0397
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
index 4318aaa41..35a488e0f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.7426 759.4176 760.5847 759.2257 0.6005
+ 768.7073 768.2559 770.1201 767.7458 1.0205
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.085 seconds)
+ **Total running time of the script:** ( 1 minutes 26.596 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_x86.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
index c47fba2fc..ad9dc67d7 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,14 +397,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -422,53 +422,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2)
- let cse_var_19: int32 = ((i.outer.inner*64) + (i.inner*16))
- let cse_var_18: int32 = (cse_var_19 + 9)
- let cse_var_17: int32 = (cse_var_19 + 8)
- let cse_var_16: int32 = (cse_var_19 + 7)
- let cse_var_15: int32 = (cse_var_19 + 6)
- let cse_var_14: int32 = (cse_var_19 + 5)
- let cse_var_13: int32 = (cse_var_19 + 4)
- let cse_var_12: int32 = (cse_var_19 + 3)
- let cse_var_11: int32 = (cse_var_19 + 2)
- let cse_var_10: int32 = (cse_var_19 + 15)
- let cse_var_9: int32 = (cse_var_19 + 14)
- let cse_var_8: int32 = (cse_var_19 + 13)
- let cse_var_7: int32 = (cse_var_19 + 12)
- let cse_var_6: int32 = (cse_var_19 + 11)
- let cse_var_5: int32 = (cse_var_19 + 10)
- let cse_var_4: int32 = (cse_var_19 + 1)
- let cse_var_3: int32 = (((floordiv(i0.outer.i1.outer.fused, 64)*4096) + (i.outer.inner*1024)) + (i.inner*256))
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 32) {
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_23: int32 = floormod(i0.outer.i1.outer.fused, 64)
- let cse_var_24: int32 = (cse_var_23*8)
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 64)*8192) + (i0.inner*512)) + cse_var_24)
- compute[ramp(cse_var_22, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_24) - (floordiv(cse_var_23, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_18: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
+ compute[cse_var_18] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_18]), 0f32)
+ }
}
}
}
@@ -524,7 +551,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 4.554 ms
+ Execution time of this operator: 1.812 ms
diff --git a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
index cfe40dced..dd4dec3cb 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:46.635** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.884** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.595 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.847 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index a8ea233db..478a48015 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 220.00/220.00 result: MeasureResult(costs=(0.0010522569862068964,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9134447574615479, timestamp=1662069506.9271834) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/220.00 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 179.14/179.14 result: MeasureResult(costs=(0.0012922816555555555,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1458566188812256, timestamp=1662088041.091059) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/179.14 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.86/260.86 result: MeasureResult(costs=(0.0008874624143646408,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.821462631225586, timestamp=1662069507.8597355) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.81/260.81 result: MeasureResult(costs=(0.0008876353535911603,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4380462169647217, timestamp=1662088041.955188) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.27/260.86 result: MeasureResult(costs=(0.04389160225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9344241619110107, timestamp=1662069512.5662534) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.35/260.86 result: MeasureResult(costs=(0.0692019565,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.679275751113892, timestamp=1662069513.8073626) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.29/260.81 result: MeasureResult(costs=(0.04375010175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8807947635650635, timestamp=1662088046.6638134) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.36/260.81 result: MeasureResult(costs=(0.0689354325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.713005542755127, timestamp=1662088047.9242866) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.08/260.86 result: MeasureResult(costs=(0.008243709785714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.303654670715332, timestamp=1662069524.8603585) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.09/260.81 result: MeasureResult(costs=(0.0082418215,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3147664070129395, timestamp=1662088058.9725747) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001284
+ Time cost of this operator: 0.001265
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
index 07be6f19c..2f4fb212c 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.4 98.722 (1, 2, 10, 10, 3) 2 1 [311.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.972 (1, 6, 10, 10) 1 1 [3.066]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 0.306 (1, 1, 10, 10, 3) 1 1 [0.965]
- Total_time - 315.432 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.1 98.705 (1, 2, 10, 10, 3) 2 1 [312.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.093 0.978 (1, 6, 10, 10) 1 1 [3.093]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.003 0.317 (1, 1, 10, 10, 3) 1 1 [1.003]
+ Total_time - 316.196 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 207.9 98.765 (1, 6, 10, 10, 1) 2 1 [207.9]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.757 0.835 (1, 6, 10, 10) 1 1 [1.757]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.401 (1, 3, 10, 10, 1) 1 1 [0.843]
- Total_time - 210.501 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.562 96.441 (1, 6, 10, 10, 1) 2 1 [81.562]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.002 2.367 (1, 6, 10, 10) 1 1 [2.002]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.008 1.192 (1, 1, 10, 10, 3) 1 1 [1.008]
+ Total_time - 84.572 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 43f5ec433..1c50abe5d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp6s63bl_j/images/random'
+ '/tmp/tmp1er51kvn/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp6s63bl_j/images/target contains 8144 images
- /tmp/tmp6s63bl_j/images/random contains 5000 images
+ /tmp/tmp1er51kvn/images/target contains 8144 images
+ /tmp/tmp1er51kvn/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 56s - loss: 0.2142 - accuracy: 0.9277 - val_loss: 0.1467 - val_accuracy: 0.9573
+ 328/328 - 57s - loss: 0.2074 - accuracy: 0.9304 - val_loss: 0.1327 - val_accuracy: 0.9585
Epoch 2/3
- 328/328 - 53s - loss: 0.0970 - accuracy: 0.9647 - val_loss: 0.1137 - val_accuracy: 0.9675
+ 328/328 - 53s - loss: 0.0980 - accuracy: 0.9621 - val_loss: 0.1232 - val_accuracy: 0.9619
Epoch 3/3
- 328/328 - 53s - loss: 0.0685 - accuracy: 0.9749 - val_loss: 0.1283 - val_accuracy: 0.9641
+ 328/328 - 53s - loss: 0.0659 - accuracy: 0.9757 - val_loss: 0.1522 - val_accuracy: 0.9490
- <keras.callbacks.History object at 0x7f68e3fac2d0>
+ <keras.callbacks.History object at 0x7f820c1c4850>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 19.302 seconds)
+ **Total running time of the script:** ( 4 minutes 46.419 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index f1b49ddf1..448acde5f 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:14.890** total execution time for **how_to_work_with_microtvm** files:
+**05:43.632** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:19.302 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:46.419 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:44.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:45.532 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.114 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.076 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.463 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.603 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 9c7d9de21..80a00fed6 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.290** total execution time for **how_to_work_with_relay** files:
+**00:44.891** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.504 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.679 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.618 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.586 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index e0c1585fd..acb795bb6 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f68d83f55f0>
+ <function my_cuda_math_rule at 0x7f81dc1bedd0>
diff --git a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
index df9a3a3e9..28da38cb3 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.299** total execution time for **how_to_work_with_schedules** files:
+**00:04.481** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.987 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.077 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.068 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.574 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.564 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.106 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.107 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.045 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 3ff1eb148..10b49d2d5 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp4uwwt9p5/input0.cc'\nsource_filename = \"/tmp/tmp4uwwt9p5/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjevgenwl/input0.cc'\nsource_filename = \"/tmp/tmpjevgenwl/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index e31474d41..ed3a80aaa 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:22.611** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:23.127** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.605 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:23.121 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index ffd74804f..c8d92663e 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 24.47s!
+ resnet18_v1 inference graph built in 25.42s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index 1284d9623..fb0bbccb8 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 17.05s!
+ yolov3-tiny inference graph built in 17.42s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index c5f485ca9..fc59ed9f9 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:34.350** total execution time for **topic_vta_tutorials_frontend** files:
+**01:35.125** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.907 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.661 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.443 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.464 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 180e68097..cfe13f086 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.294** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.390** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.888 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.949 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.406 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.441 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 667176497..55550213e 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.751** total execution time for **topic_vta_tutorials** files:
+**00:00.778** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.394 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.407 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.357 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.371 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 8444dd6ae..5fff84024 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E*E*E
+
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.482 ms
+ Execution time of this operator: 93.643 ms
@@ -426,7 +433,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- *E
+
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.929 seconds)
+ **Total running time of the script:** ( 1 minutes 20.055 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index ea3b3f3b5..dd359ce14 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.73/10.73 result: MeasureResult(costs=(0.0250270704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5421488285064697, timestamp=1662068235.1642473) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.97/10.73 result: MeasureResult(costs=(0.0905125636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.600559949874878, timestamp=1662068237.334488) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.74/11.74 result: MeasureResult(costs=(0.022861272999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6028172969818115, timestamp=1662068237.9074042) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.74 result: MeasureResult(costs=(0.1451686174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4464380741119385, timestamp=1662068240.9443283) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.62/11.74 result: MeasureResult(costs=(0.0741612326,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3298187255859375, timestamp=1662068242.4052653) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.75/11.74 result: MeasureResult(costs=(0.153383455,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.577357292175293, timestamp=1662068245.5663548) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.86/11.74 result: MeasureResult(costs=(0.31237713619999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.1237170696258545, timestamp=1662068250.7292414) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.37/11.74 result: MeasureResult(costs=(0.0258894444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5589416027069092, timestamp=1662068251.3078663) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.89/11.74 result: MeasureResult(costs=(0.141971067,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3767287731170654, timestamp=1662068253.8058078) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.75/11.74 result: MeasureResult(costs=(0.0976513352,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6692326068878174, timestamp=1662068255.5322173) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.08/9.08 result: MeasureResult(costs=(0.029560945600000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6118500232696533, timestamp=1662086723.6378741) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.52/9.08 result: MeasureResult(costs=(0.10643780939999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8589472770690918, timestamp=1662086725.506462) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.60/11.60 result: MeasureResult(costs=(0.0231429856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5577545166015625, timestamp=1662086726.6088662) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.78/11.60 result: MeasureResult(costs=(0.1511432346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5453879833221436, timestamp=1662086729.757379) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.63/11.60 result: MeasureResult(costs=(0.07393550219999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3240461349487305, timestamp=1662086731.214074) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.79/11.60 result: MeasureResult(costs=(0.1499543998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.568110227584839, timestamp=1662086733.8204923) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.60 result: MeasureResult(costs=(0.3073258002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.045556306838989, timestamp=1662086739.4816482) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.60/11.60 result: MeasureResult(costs=(0.025315159800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5546350479125977, timestamp=1662086740.0543113) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.76/11.60 result: MeasureResult(costs=(0.15244594360000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.54144287109375, timestamp=1662086742.7160997) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.52/11.60 result: MeasureResult(costs=(0.106664245,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8219544887542725, timestamp=1662086744.595707) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 9a34dc3d0..29eccecb2 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 498.28129317001185, 'median': 498.2503235000195, 'std': 1.062073502571041}
+ {'mean': 499.802830790004, 'median': 499.61831065002116, 'std': 0.6728640250425578}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.46/ 17.46 GFLOPS | Progress: (4/20) | 6.46 s
[Task 1/25] Current/Best: 6.15/ 17.46 GFLOPS | Progress: (8/20) | 9.41 s
[Task 1/25] Current/Best: 11.15/ 22.65 GFLOPS | Progress: (12/20) | 11.91 s
[Task 1/25] Current/Best: 16.46/ 22.77 GFLOPS | Progress: (16/20) | 13.60 s
[Task 1/25] Current/Best: 11.59/ 23.72 GFLOPS | Progress: (20/20) | 15.39 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.30/ 12.92 GFLOPS | Progress: (4/20) | 3.84 s
[Task 2/25] Current/Best: 13.55/ 18.23 GFLOPS | Progress: (8/20) | 5.14 s
[Task 2/25] Current/Best: 20.78/ 20.78 GFLOPS | Progress: (12/20) | 6.46 s
[Task 2/25] Current/Best: 11.37/ 20.78 GFLOPS | Progress: (16/20) | 7.73 s
[Task 2/25] Current/Best: 20.18/ 20.78 GFLOPS | Progress: (20/20) | 9.35 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.81 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.20/ 16.69 GFLOPS | Progress: (8/20) | 7.85 s
[Task 3/25] Current/Best: 14.93/ 16.69 GFLOPS | Progress: (12/20) | 9.58 s
[Task 3/25] Current/Best: 7.20/ 21.29 GFLOPS | Progress: (16/20) | 11.53 s
[Task 3/25] Current/Best: 12.57/ 21.29 GFLOPS | Progress: (20/20) | 16.12 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.52/ 20.18 GFLOPS | Progress: (4/20) | 2.46 s
[Task 4/25] Current/Best: 6.81/ 20.18 GFLOPS | Progress: (8/20) | 7.20 s
[Task 4/25] Current/Best: 21.99/ 21.99 GFLOPS | Progress: (12/20) | 12.22 s
[Task 4/25] Current/Best: 16.54/ 21.99 GFLOPS | Progress: (16/20) | 14.63 s
[Task 4/25] Current/Best: 13.24/ 21.99 GFLOPS | Progress: (20/20) | 16.75 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.63/ 10.07 GFLOPS | Progress: (4/20) | 2.64 s
[Task 5/25] Current/Best: 11.62/ 12.58 GFLOPS | Progress: (8/20) | 4.72 s
[Task 5/25] Current/Best: 10.86/ 17.94 GFLOPS | Progress: (12/20) | 7.81 s
[Task 5/25] Current/Best: 11.78/ 22.38 GFLOPS | Progress: (16/20) | 9.23 s
[Task 5/25] Current/Best: 12.09/ 22.38 GFLOPS | Progress: (20/20) | 11.16 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.11/ 20.09 GFLOPS | Progress: (4/20) | 4.17 s
[Task 6/25] Current/Best: 18.94/ 20.09 GFLOPS | Progress: (8/20) | 5.96 s
[Task 6/25] Current/Best: 13.32/ 20.09 GFLOPS | Progress: (12/20) | 7.91 s
[Task 6/25] Current/Best: 19.57/ 20.09 GFLOPS | Progress: (16/20) | 10.16 s
[Task 6/25] Current/Best: 3.75/ 20.09 GFLOPS | Progress: (20/20) | 12.68 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.01/ 12.73 GFLOPS | Progress: (4/20) | 3.71 s
[Task 7/25] Current/Best: 19.87/ 20.43 GFLOPS | Progress: (8/20) | 5.25 s
[Task 7/25] Current/Best: 13.14/ 20.66 GFLOPS | Progress: (12/20) | 7.22 s
[Task 7/25] Current/Best: 12.18/ 20.77 GFLOPS | Progress: (16/20) | 9.27 s
[Task 7/25] Current/Best: 6.32/ 21.68 GFLOPS | Progress: (20/20) | 11.74 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.08/ 14.20 GFLOPS | Progress: (4/20) | 2.95 s
[Task 8/25] Current/Best: 9.44/ 14.20 GFLOPS | Progress: (8/20) | 8.17 s
[Task 8/25] Current/Best: 13.48/ 14.20 GFLOPS | Progress: (12/20) | 14.77 s
[Task 8/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (16/20) | 16.89 s
[Task 8/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (20/20) | 23.99 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.24/ 15.48 GFLOPS | Progress: (4/20) | 12.00 s
[Task 9/25] Current/Best: 23.35/ 23.35 GFLOPS | Progress: (8/20) | 13.83 s
[Task 9/25] Current/Best: 8.15/ 23.35 GFLOPS | Progress: (12/20) | 16.39 s
[Task 9/25] Current/Best: 17.96/ 23.35 GFLOPS | Progress: (16/20) | 19.29 s
[Task 9/25] Current/Best: 9.09/ 23.35 GFLOPS | Progress: (20/20) | 27.96 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (4/20) | 2.61 s
[Task 10/25] Current/Best: 15.63/ 18.21 GFLOPS | Progress: (8/20) | 4.27 s
[Task 10/25] Current/Best: 12.58/ 18.67 GFLOPS | Progress: (12/20) | 5.84 s
[Task 10/25] Current/Best: 19.15/ 20.38 GFLOPS | Progress: (16/20) | 6.96 s
[Task 10/25] Current/Best: 8.98/ 20.38 GFLOPS | Progress: (20/20
) | 8.53 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.26/ 18.07 GFLOPS | Progress: (4/20) | 3.45 s
[Task 11/25] Current/Best: 16.91/ 18.07 GFLOPS | Progress: (8/20) | 6.27 s
[Task 11/25] Current/Best: 16.29/ 18.07 GFLOPS | Progress: (12/20) | 8.39 s
[Task 11/25] Current/Best: 11.87/ 20.83 GFLOPS | Progress: (16/20) | 11.30 s
[Task 11/25] Current/Best: 19.41/ 21.57 GFLOPS | Progress: (20/20) | 13.42 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.78/ 18.00 GFLOPS | Progress: (4/20) | 5.81 s
[Task 12/25] Current/Best: 5.23/ 18.00 GFLOPS | Progress: (8/20) | 9.81 s
[Task 12/25] Current/Best: 18.93/ 18.98 GFLOPS | Progress: (12/20) | 11.82 s
[Task 12/25] Current/Best: 15.15/ 18.98 GFLOPS | Progress: (16/20) | 14.76 s
[Task 12/25] Current/Best: 15.04/ 18.98 GFLOPS | Progress: (20/20) | 16.73 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.26/ 17.23 GFLOPS | Progress: (4/20) | 3.80 s
[Task 13/25] Current/Best: 15.17/ 20.62 GFLOPS | Progress: (8/20) | 6.45 s
[Task 13/25] Current/Best: 19.44/ 21.39 GFLOPS | Progress: (12/20) | 9.62 s
[Task 13/25] Current/Best: 12.22/ 21.39 GFLOPS | Progress: (16/20) | 13.13 s
[Task 13/25] Current/Best: 18.49/ 21.39 GFLOPS | Progress: (20/20) | 15.50 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.72/ 13.72 GFLOPS | Progress: (4/20) | 3.48 s
[Task 14/25] Current/Best: 6.06/ 13.72 GFLOPS | Progress: (8/20) | 5.66 s
[Task 14/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (12/20) | 8.33 s
[Task 14/25] Current/Best: 16.18/ 20.32 GFLOPS | Progress: (16/20) | 10.00 s Done.
-
[Task 14/25] Current/Best: 17.06/ 20.32 GFLOPS | Progress: (20/20) | 11.79 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.11/ 17.67 GFLOPS | Progress: (4/20) | 2.80 s
[Task 15/25] Current/Best: 13.82/ 17.94 GFLOPS | Progress: (8/20) | 4.09 s
[Task 15/25] Current/Best: 10.31/ 22.22 GFLOPS | Progress: (12/20) | 6.30 s
[Task 15/25] Current/Best: 20.36/ 22.22 GFLOPS | Progress: (16/20) | 9.52 s
[Task 15/25] Current/Best: 9.64/ 22.22 GFLOPS | Progress: (20/20) | 10.55 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.72/ 19.72 GFLOPS | Progress: (4/20) | 3.05 s
[Task 16/25] Current/Best: 3.04/ 19.72 GFLOPS | Progress: (8/20) | 4.67 s
[Task 16/25] Current/Best: 18.92/ 19.72 GFLOPS | Progress: (12/20) | 5.90 s
[Task 16/25] Current/Best: 17.72/ 19.72 GFLOPS | Progress: (16/20) |
7.28 s
[Task 16/25] Current/Best: 10.00/ 21.54 GFLOPS | Progress: (20/20) | 9.45 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.42/ 18.08 GFLOPS | Progress: (4/20) | 4.85 s
[Task 17/25] Current/Best: 14.52/ 23.09 GFLOPS | Progress: (8/20) | 7.79 s
[Task 17/25] Current/Best: 17.48/ 23.09 GFLOPS | Progress: (12/20) | 9.84 s
[Task 17/25] Current/Best: 16.44/ 23.09 GFLOPS | Progress: (16/20) | 12.06 s
[Task 17/25] Current/Best: 9.98/ 23.09 GFLOPS | Progress: (20/20) | 14.25 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.14/ 17.92 GFLOPS | Progress: (4/20) | 3.87 s
[Task 18/25] Current/Best: 10.57/ 19.04 GFLOPS | Progress: (8/20) | 7.58 s
[Task 18/25] Current/Best: 19.54/ 19.54 GFLOPS | Progress: (12/20) | 9.54 s
[Task 18/25] Current/Best: 10.04/ 19.54 GFLOPS | Progress: (16/20) | 13.45 s
[Task 18/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (20/20) | 14.97 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.48/ 20.20 GFLOPS | Progress: (4/20) | 6.40 s
[Task 19/25] Current/Best: 2.69/ 20.20 GFLOPS | Progress: (8/20) | 9.73 s
[Task 19/25] Current/Best: 19.22/ 20.74 GFLOPS | Progress: (12/20) | 12.70 s
[Task 19/25] Current/Best: 15.12/ 21.09 GFLOPS | Progress: (16/20) | 15.70 s
[Task 19/25] Current/Best: 2.70/ 22.48 GFLOPS | Progress: (20/20) | 18.52 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.46/ 15.18 GFLOPS | Progress: (4/20) | 3.48 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 6.64 s
[Task 1/25] Current/Best: 6.14/ 17.47 GFLOPS | Progress: (8/20) | 9.74 s
[Task 1/25] Current/Best: 11.48/ 22.61 GFLOPS | Progress: (12/20) | 12.24 s
[Task 1/25] Current/Best: 16.39/ 22.68 GFLOPS | Progress: (16/20) | 13.96 s
[Task 1/25] Current/Best: 11.59/ 23.71 GFLOPS | Progress: (20/20) | 15.72 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.16/ 13.39 GFLOPS | Progress: (4/20) | 4.04 s
[Task 2/25] Current/Best: 14.06/ 17.90 GFLOPS | Progress: (8/20) | 5.39 s
[Task 2/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (12/20) | 6.73 s
[Task 2/25] Current/Best: 12.45/ 20.61 GFLOPS | Progress: (16/20) | 8.06 s
[Task 2/25] Current/Best: 18.81/ 20.61 GFLOPS | Progress: (20/20) | 9.73 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.75 GFLOPS | Progress: (4/20) | 5.96 s
[Task 3/25] Current/Best: 15.21/ 16.74 GFLOPS | Progress: (8/20) | 7.91 s
[Task 3/25] Current/Best: 14.87/ 16.74 GFLOPS | Progress: (12/20) | 9.69 s
[Task 3/25] Current/Best: 7.17/ 23.64 GFLOPS | Progress: (16/20) | 11.63 s
[Task 3/25] Current/Best: 12.56/ 23.64 GFLOPS | Progress: (20/20) | 16.27 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.49/ 19.89 GFLOPS | Progress: (4/20) | 2.50 s
[Task 4/25] Current/Best: 6.76/ 19.89 GFLOPS | Progress: (8/20) | 7.37 s
[Task 4/25] Current/Best: 20.93/ 20.93 GFLOPS | Progress: (12/20) | 12.51 s
[Task 4/25] Current/Best: 16.83/ 20.93 GFLOPS | Progress: (16/20) | 15.00 s
[Task 4/25] Current/Best: 12.90/ 20.93 GFLOPS | Progress: (20/20) | 17.09 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.70/ 10.24 GFLOPS | Progress: (4/20) | 2.68 s
[Task 5/25] Current/Best: 11.73/ 13.10 GFLOPS | Progress: (8/20) | 4.75 s
[Task 5/25] Current/Best: 9.69/ 17.91 GFLOPS | Progress: (12/20) | 8.05 s
[Task 5/25] Current/Best: 11.71/ 22.17 GFLOPS | Progress: (16/20) | 9.48 s
[Task 5/25] Current/Best: 11.70/ 22.17 GFLOPS | Progress: (20/20) | 11.44 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.14/ 20.06 GFLOPS | Progress: (4/20) | 4.24 s
[Task 6/25] Current/Best: 18.89/ 20.06 GFLOPS | Progress: (8/20) | 6.02 s
[Task 6/25] Current/Best: 13.08/ 20.06 GFLOPS | Progress: (12/20) | 7.99 s
[Task 6/25] Current/Best: 19.40/ 20.06 GFLOPS | Progress: (16/20) | 10.26 s
[Task 6/25] Current/Best: 3.75/ 20.06 GFLOPS | Progress: (20/20) | 12.79 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.82/ 12.45 GFLOPS | Progress: (4/20) | 3.72 s
[Task 7/25] Current/Best: 19.61/ 21.15 GFLOPS | Progress: (8/20) | 5.28 s
[Task 7/25] Current/Best: 15.22/ 21.15 GFLOPS | Progress: (12/20) | 7.22 s
[Task 7/25] Current/Best: 12.18/ 21.15 GFLOPS | Progress: (16/20) | 9.29 s
[Task 7/25] Current/Best: 6.43/ 21.67 GFLOPS | Progress: (20/20) | 11.77 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.20/ 13.29 GFLOPS | Progress: (4/20) | 3.06 s
[Task 8/25] Current/Best: 9.68/ 13.29 GFLOPS | Progress: (8/20) | 8.30 s
[Task 8/25] Current/Best: 13.58/ 13.74 GFLOPS | Progress: (12/20) | 15.02 s
[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (16/20) | 17.12 s
[Task 8/25] Current/Best: 19.40/ 19.40 GFLOPS | Progress: (20/20) | 24.33 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.16/ 15.55 GFLOPS | Progress: (4/20) | 12.06 s
[Task 9/25] Current/Best: 23.28/ 23.28 GFLOPS | Progress: (8/20) | 13.90 s
[Task 9/25] Current/Best: 8.20/ 23.28 GFLOPS | Progress: (12/20) | 16.49 s
[Task 9/25] Current/Best: 17.76/ 23.28 GFLOPS | Progress: (16/20) | 19.45 s
[Task 9/25] Current/Best: 9.03/ 23.28 GFLOPS | Progress: (20/20) | 28.36 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.99/ 17.99 GFLOPS | Progress: (4/20) | 2.69 s
[Task 10/25] Current/Best: 15.73/ 17.99 GFLOPS | Progress: (8/20) | 4.37 s
[Task 10/25] Current/Best: 12.63/ 19.18 GFLOPS | Progress: (12/20) | 5.95 s
[Task 10/25] Current/Best: 18.94/ 20.16 GFLOPS | Progress: (16/20) | 7.08 s
[Task 10/25] Current/Best: 8.88/ 20.16 GFLOPS | Progress: (20/20
) | 8.64 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.21/ 18.09 GFLOPS | Progress: (4/20) | 3.49 s
[Task 11/25] Current/Best: 16.52/ 18.09 GFLOPS | Progress: (8/20) | 6.35 s
[Task 11/25] Current/Best: 17.94/ 18.09 GFLOPS | Progress: (12/20) | 8.44 s
[Task 11/25] Current/Best: 13.38/ 20.88 GFLOPS | Progress: (16/20) | 11.38 s
[Task 11/25] Current/Best: 19.41/ 21.58 GFLOPS | Progress: (20/20) | 13.51 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.16 GFLOPS | Progress: (4/20) | 5.99 s
[Task 12/25] Current/Best: 5.31/ 18.16 GFLOPS | Progress: (8/20) | 10.00 s
[Task 12/25] Current/Best: 18.92/ 18.98 GFLOPS | Progress: (12/20) | 11.99 s
[Task 12/25] Current/Best: 13.54/ 18.98 GFLOPS | Progress: (16/20) | 15.00 s
[Task 12/25] Current/Best: 15.26/ 19.15 GFLOPS | Progress: (20/20) | 16.92 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.90/ 17.29 GFLOPS | Progress: (4/20) | 3.85 s
[Task 13/25] Current/Best: 15.62/ 20.64 GFLOPS | Progress: (8/20) | 6.51 s
[Task 13/25] Current/Best: 19.44/ 21.11 GFLOPS | Progress: (12/20) | 9.61 s
[Task 13/25] Current/Best: 12.21/ 21.11 GFLOPS | Progress: (16/20) | 13.13 s
[Task 13/25] Current/Best: 18.40/ 21.11 GFLOPS | Progress: (20/20) | 15.46 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.73/ 13.73 GFLOPS | Progress: (4/20) | 3.53 s
[Task 14/25] Current/Best: 6.10/ 13.73 GFLOPS | Progress: (8/20) | 5.74 s
[Task 14/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (12/20) | 8.45 s
[Task 14/25] Current/Best: 16.32/ 20.54 GFLOPS | Progress: (16/20) | 10.15 s Done.
+
[Task 14/25] Current/Best: 17.03/ 20.54 GFLOPS | Progress: (20/20) | 11.92 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.11/ 16.84 GFLOPS | Progress: (4/20) | 2.88 s
[Task 15/25] Current/Best: 14.23/ 17.99 GFLOPS | Progress: (8/20) | 4.15 s
[Task 15/25] Current/Best: 10.33/ 22.25 GFLOPS | Progress: (12/20) | 6.41 s
[Task 15/25] Current/Best: 20.34/ 22.25 GFLOPS | Progress: (16/20) | 10.15 s
[Task 15/25] Current/Best: 9.68/ 22.25 GFLOPS | Progress: (20/20) | 11.18 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.39/ 20.39 GFLOPS | Progress: (4/20) | 3.14 s
[Task 16/25] Current/Best: 3.02/ 20.39 GFLOPS | Progress: (8/20) | 4.77 s
[Task 16/25] Current/Best: 19.73/ 20.39 GFLOPS | Progress: (12/20) | 6.00 s
[Task 16/25] Current/Best: 17.68/ 20.39 GFLOPS | Progress: (16/20)
| 7.39 s
[Task 16/25] Current/Best: 9.88/ 21.79 GFLOPS | Progress: (20/20) | 9.60 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.52/ 18.19 GFLOPS | Progress: (4/20) | 4.95 s
[Task 17/25] Current/Best: 13.85/ 23.09 GFLOPS | Progress: (8/20) | 7.92 s
[Task 17/25] Current/Best: 18.08/ 23.09 GFLOPS | Progress: (12/20) | 9.99 s
[Task 17/25] Current/Best: 16.44/ 23.09 GFLOPS | Progress: (16/20) | 12.24 s
[Task 17/25] Current/Best: 10.02/ 23.09 GFLOPS | Progress: (20/20) | 14.45 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.53/ 18.00 GFLOPS | Progress: (4/20) | 3.92 s
[Task 18/25] Current/Best: 10.63/ 19.84 GFLOPS | Progress: (8/20) | 7.68 s
[Task 18/25] Current/Best: 19.26/ 19.84 GFLOPS | Progress: (12/20) | 9.63 s
[Task 18/25] Current/Best: 9.76/ 19.84 GFLOPS | Progress: (16/20) | 13.60 s
[Task 18/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (20/20) | 15.15 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.22/ 20.09 GFLOPS | Progress: (4/20) | 6.43 s
[Task 19/25] Current/Best: 2.69/ 20.09 GFLOPS | Progress: (8/20) | 9.75 s
[Task 19/25] Current/Best: 19.17/ 20.69 GFLOPS | Progress: (12/20) | 12.79 s
[Task 19/25] Current/Best: 13.90/ 21.40 GFLOPS | Progress: (16/20) | 15.83 s
[Task 19/25] Current/Best: 2.70/ 22.36 GFLOPS | Progress: (20/20) | 18.64 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.55/ 14.87 GFLOPS | Progress: (4/20) | 3.47 s Done.
Done.
-
[Task 20/25] Current/Best: 10.14/ 15.18 GFLOPS | Progress: (8/20) | 7.07 s
[Task 20/25] Current/Best: 2.32/ 16.39 GFLOPS | Progress: (12/20) | 11.10 s
[Task 20/25] Current/Best: 12.12/ 16.39 GFLOPS | Progress: (16/20) | 15.10 s
[Task 20/25] Current/Best: 13.32/ 21.53 GFLOPS | Progress: (20/20) | 17.28 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.59 GFLOPS | Progress: (4/20) | 3.37 s
[Task 21/25] Current/Best: 14.35/ 17.59 GFLOPS | Progress: (8/20) | 5.03 s
[Task 21/25] Current/Best: 1.61/ 17.59 GFLOPS | Progress: (12/20) | 7.21 s
[Task 21/25] Current/Best: 18.15/ 18.15 GFLOPS | Progress: (16/20) | 10.80 s
[Task 21/25] Current/Best: 4.46/ 18.15 GFLOPS | Progress: (20/20) | 18.24 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.99 GFLOPS | Progress: (4/20
) | 2.73 s
[Task 22/25] Current/Best: 8.95/ 21.84 GFLOPS | Progress: (8/20) | 4.72 s
[Task 22/25] Current/Best: 19.55/ 21.84 GFLOPS | Progress: (12/20) | 7.11 s
[Task 22/25] Current/Best: 15.44/ 21.84 GFLOPS | Progress: (16/20) | 9.26 s
[Task 22/25] Current/Best: 14.99/ 21.84 GFLOPS | Progress: (20/20) | 11.04 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.30/ 20.21 GFLOPS | Progress: (4/20) | 3.34 s
[Task 23/25] Current/Best: 15.51/ 20.21 GFLOPS | Progress: (8/20) | 6.78 s
[Task 23/25] Current/Best: 20.69/ 21.13 GFLOPS | Progress: (12/20) | 8.67 s
[Task 23/25] Current/Best: 6.11/ 21.13 GFLOPS | Progress: (16/20) | 15.78 s
[Task 23/25] Current/Best: 7.30/ 21.13 GFLOPS | Progress: (20/20) | 20.07 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.58/ 8.58 GFLOPS | Progress: (4/20) | 11.86 s
[Task 24/25] Current/Best: 3.32/ 8.58 GFLOPS | Progress: (8/20) | 23.15 s
[Task 24/25] Current/Best: 4.27/ 8.58 GFLOPS | Progress: (12/20) | 33.88 s Done.
-
[Task 24/25] Current/Best: 6.97/ 8.81 GFLOPS | Progress: (16/20) | 39.70 s
[Task 24/25] Current/Best: 3.29/ 8.89 GFLOPS | Progress: (20/20) | 45.75 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.94 GFLOPS | Progress: (4/20) | 11.65 s
[Task 25/25] Current/Best: 5.83/ 7.50 GFLOPS | Progress: (8/20) | 23.00 s
[Task 25/25] Current/Best: 5.92/ 7.50 GFLOPS | Progress: (12/20) | 34.46 s
[Task 25/25] Current/Best: 5.65/ 8.38 GFLOPS | Progress: (16/20) | 36.28 s
[Task 25/25] Current/Best: 2.90/ 8.63 GFLOPS | Progress: (20/20) | 46.96 s
+
[Task 20/25] Current/Best: 10.15/ 14.87 GFLOPS | Progress: (8/20) | 7.06 s
[Task 20/25] Current/Best: 2.33/ 14.87 GFLOPS | Progress: (12/20) | 11.21 s
[Task 20/25] Current/Best: 12.50/ 14.87 GFLOPS | Progress: (16/20) | 15.06 s
[Task 20/25] Current/Best: 13.20/ 21.52 GFLOPS | Progress: (20/20) | 17.19 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.42 GFLOPS | Progress: (4/20) | 3.41 s
[Task 21/25] Current/Best: 14.38/ 17.42 GFLOPS | Progress: (8/20) | 5.05 s
[Task 21/25] Current/Best: 1.61/ 17.42 GFLOPS | Progress: (12/20) | 7.26 s
[Task 21/25] Current/Best: 17.92/ 17.92 GFLOPS | Progress: (16/20) | 10.87 s
[Task 21/25] Current/Best: 4.46/ 17.92 GFLOPS | Progress: (20/20) | 18.45 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20
) | 2.80 s
[Task 22/25] Current/Best: 9.14/ 21.13 GFLOPS | Progress: (8/20) | 4.84 s
[Task 22/25] Current/Best: 19.49/ 21.13 GFLOPS | Progress: (12/20) | 7.27 s
[Task 22/25] Current/Best: 14.82/ 21.13 GFLOPS | Progress: (16/20) | 9.43 s
[Task 22/25] Current/Best: 13.85/ 21.13 GFLOPS | Progress: (20/20) | 11.21 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.33/ 20.03 GFLOPS | Progress: (4/20) | 3.32 s
[Task 23/25] Current/Best: 15.98/ 20.03 GFLOPS | Progress: (8/20) | 6.74 s
[Task 23/25] Current/Best: 20.80/ 20.94 GFLOPS | Progress: (12/20) | 8.63 s
[Task 23/25] Current/Best: 5.79/ 20.94 GFLOPS | Progress: (16/20) | 16.04 s
[Task 23/25] Current/Best: 7.44/ 20.94 GFLOPS | Progress: (20/20) | 20.38 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (4/20) | 11.88 s
[Task 24/25] Current/Best: 2.03/ 8.72 GFLOPS | Progress: (8/20) | 22.94 s
[Task 24/25] Current/Best: 4.00/ 8.72 GFLOPS | Progress: (12/20) | 34.53 s Done.
+
[Task 24/25] Current/Best: 7.19/ 8.72 GFLOPS | Progress: (16/20) | 40.37 s
[Task 24/25] Current/Best: 3.16/ 8.72 GFLOPS | Progress: (20/20) | 46.43 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.53/ 2.64 GFLOPS | Progress: (4/20) | 11.65 s
[Task 25/25] Current/Best: 5.58/ 7.42 GFLOPS | Progress: (8/20) | 23.10 s
[Task 25/25] Current/Best: 5.76/ 7.42 GFLOPS | Progress: (12/20) | 34.63 s
[Task 25/25] Current/Best: 5.75/ 8.91 GFLOPS | Progress: (16/20) | 36.41 s
[Task 25/25] Current/Best: 2.91/ 8.91 GFLOPS | Progress: (20/20) | 47.13 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 412.65750754999317, 'median': 412.5496574499948, 'std': 1.2876633708013223}
- unoptimized: {'mean': 498.28129317001185, 'median': 498.2503235000195, 'std': 1.062073502571041}
+ optimized: {'mean': 420.08675765000135, 'median': 419.96661005000533, 'std': 1.1592090723124646}
+ unoptimized: {'mean': 499.802830790004, 'median': 499.61831065002116, 'std': 0.6728640250425578}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 31.664 seconds)
+ **Total running time of the script:** ( 10 minutes 43.302 seconds)
.. _sphx_glr_download_tutorial_autotvm_relay_x86.py:
diff --git a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
index 4bf8df2ad..0de761346 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.245e-07 secs/op
+ 1.962e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index decc34913..27dd63332 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xc6b80b0)), stage(b, placeholder(b, 0x11e4c040)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x22141770)), stage(b, placeholder(b, 0xbaf2570)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 1c79f003a..6b67ad9cc 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**13:40.937** total execution time for **tutorial** files:
+**14:01.910** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:31.664 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:43.302 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:09.929 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:20.055 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.319 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.560 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.652 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.820 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.987 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.721 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.710 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.731 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.517 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.151 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.174 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index d0c3fcc85..26829ec7b 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000024
+ vector: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.837640000616374e-06 1.0
- naive 5.8123e-06 0.7415880289912402
- parallel 5.9991e-06 0.7654217340332311
- vector 2.44991e-05 3.1258261412967836
+ numpy 8.49372000175208e-06 1.0
+ naive 5.8365e-06 0.6871547447756754
+ parallel 6.3236e-06 0.7445029973551719
+ vector 2.46044e-05 2.8967754994189376
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019151
+ Numpy running time: 0.018955
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.473850
+ none: 3.305902
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.322162
+ blocking: 0.341165
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.349305
+ vectorization: 0.357151
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.126571
+ loop permutation: 0.132203
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.109158
+ array packing: 0.109336
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111102
+ block caching: 0.111286
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.146828
+ parallelization: 0.147921
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4738499142 1.0
- blocking 0.3221618066 0.09273912648992243
- vectorization 0.3493052523 0.10055277600570783
- loop permutation 0.1265713203 0.03643546020299163
- array packing 0.10915846790000001 0.031422908472180884
- block caching 0.11110223150000001 0.031982450089697086
- parallelization 0.1468277371 0.04226657475897696
+ none 3.3059015802000005 1.0
+ blocking 0.3411653609 0.10319888618080401
+ vectorization 0.3571509433 0.10803435451287485
+ loop permutation 0.13220253990000003 0.03998985955655765
+ array packing 0.1093361253 0.03307301280680757
+ block caching 0.1112863906 0.03366294727783983
+ parallelization 0.1479214063 0.044744649140780246
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.319 seconds)
+ **Total running time of the script:** ( 1 minutes 0.560 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 0f4d89a2e..98dfc824f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-54786bbff340426109de7785bb2de4c1dfc2a738
+8ca8f24d54d65be552448e5368d879710930711b
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index f11e844b8..f71cf86eb 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.009 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.695 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index d27fcc298..1e540040a 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip07db3c73-3db9-48d3-8230-c7f829dd6103 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2f5c0f38-d1e0-45cc-b314-3bd3b27fc4ff from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index d7724324f..ecd9ce49f 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,13 +432,13 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 56.3MB/s]
- 28%|##8 | 11.7M/41.5M [00:00<00:00, 47.4MB/s]
- 39%|###9 | 16.3M/41.5M [00:00<00:00, 29.0MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 35.5MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 45.9MB/s]
- 96%|#########6| 40.0M/41.5M [00:00<00:00, 52.8MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 46.9MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 42.4MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 44.5MB/s]
+ 45%|####4 | 18.6M/41.5M [00:00<00:00, 42.5MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 37.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.0MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 39.5MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 41.3MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 8d118f098..df3bf1ca6 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 41%|#### | 18.1M/44.7M [00:00<00:00, 190MB/s]
- 92%|#########2| 41.2M/44.7M [00:00<00:00, 221MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 221MB/s]
+ 38%|###8 | 17.0M/44.7M [00:00<00:00, 178MB/s]
+ 76%|#######6 | 34.0M/44.7M [00:00<00:00, 174MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 188MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index ed1d987d8..9846fa3ae 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.757 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.813 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 49b3c2b6c..f68c6caba 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:08.355</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:24.015</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -335,44 +335,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:04.009</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:08.813</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:03.757</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
+<td><p>01:06.695</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:40.478</p></td>
+<td><p>00:41.964</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:28.872</p></td>
+<td><p>00:30.046</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.447</p></td>
+<td><p>00:26.766</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.569</p></td>
+<td><p>00:26.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.419</p></td>
+<td><p>00:22.986</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:20.036</p></td>
+<td><p>00:20.809</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:16.406</p></td>
+<td><p>00:17.295</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.362</p></td>
+<td><p>00:02.632</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index f8c9dbcfb..32f41639d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.5967 16.3693 17.2798 16.0005 0.5185
+ 16.4733 16.3969 17.3753 16.1531 0.3131
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
index ec4fd2d2f..51391ef55 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,16 +436,49 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|1 | 3.21M/170M [00:00<00:05, 33.7MB/s]
- 4%|3 | 6.50M/170M [00:00<00:05, 34.1MB/s]
- 14%|#4 | 23.9M/170M [00:00<00:01, 102MB/s]
- 28%|##8 | 47.8M/170M [00:00<00:00, 161MB/s]
- 43%|####2 | 72.5M/170M [00:00<00:00, 196MB/s]
- 57%|#####7 | 97.3M/170M [00:00<00:00, 218MB/s]
- 70%|####### | 119M/170M [00:00<00:00, 222MB/s]
- 84%|########3 | 142M/170M [00:00<00:00, 228MB/s]
- 97%|#########6| 164M/170M [00:00<00:00, 228MB/s]
-100%|##########| 170M/170M [00:00<00:00, 192MB/s]
+ 3%|3 | 5.12M/170M [00:00<00:03, 53.7MB/s]
+ 6%|6 | 10.2M/170M [00:00<00:04, 36.3MB/s]
+ 8%|8 | 14.0M/170M [00:00<00:04, 34.5MB/s]
+ 11%|#1 | 19.3M/170M [00:00<00:03, 41.3MB/s]
+ 15%|#5 | 26.2M/170M [00:00<00:03, 49.5MB/s]
+ 19%|#9 | 32.8M/170M [00:00<00:02, 55.5MB/s]
+ 24%|##3 | 40.6M/170M [00:00<00:02, 63.6MB/s]
+ 28%|##7 | 46.9M/170M [00:00<00:02, 60.2MB/s]
+ 31%|###1 | 52.8M/170M [00:01<00:02, 58.7MB/s]
+ 34%|###4 | 58.5M/170M [00:01<00:03, 36.4MB/s]
+ 37%|###7 | 63.0M/170M [00:01<00:02, 37.4MB/s]
+ 40%|###9 | 67.4M/170M [00:01<00:02, 37.3MB/s]
+ 42%|####2 | 71.4M/170M [00:01<00:02, 37.6MB/s]
+ 44%|####4 | 75.4M/170M [00:01<00:02, 34.4MB/s]
+ 46%|####6 | 79.0M/170M [00:02<00:02, 32.1MB/s]
+ 48%|####8 | 82.2M/170M [00:02<00:02, 31.1MB/s]
+ 51%|##### | 85.8M/170M [00:02<00:02, 32.6MB/s]
+ 52%|#####2 | 89.0M/170M [00:02<00:02, 28.7MB/s]
+ 54%|#####4 | 91.9M/170M [00:02<00:03, 26.6MB/s]
+ 56%|#####5 | 94.8M/170M [00:02<00:02, 27.0MB/s]
+ 58%|#####7 | 97.9M/170M [00:02<00:02, 28.5MB/s]
+ 59%|#####9 | 101M/170M [00:02<00:02, 28.7MB/s]
+ 61%|###### | 104M/170M [00:02<00:02, 28.8MB/s]
+ 63%|######2 | 106M/170M [00:03<00:02, 28.8MB/s]
+ 64%|######4 | 109M/170M [00:03<00:02, 29.3MB/s]
+ 66%|######6 | 112M/170M [00:03<00:02, 26.4MB/s]
+ 68%|######7 | 115M/170M [00:03<00:02, 28.0MB/s]
+ 70%|######9 | 119M/170M [00:03<00:01, 30.2MB/s]
+ 72%|#######1 | 122M/170M [00:03<00:01, 30.3MB/s]
+ 73%|#######3 | 125M/170M [00:03<00:01, 26.1MB/s]
+ 75%|#######5 | 128M/170M [00:03<00:01, 26.9MB/s]
+ 78%|#######7 | 132M/170M [00:03<00:01, 31.4MB/s]
+ 80%|#######9 | 135M/170M [00:04<00:01, 29.7MB/s]
+ 82%|########1 | 139M/170M [00:04<00:01, 32.4MB/s]
+ 84%|########3 | 142M/170M [00:04<00:00, 33.0MB/s]
+ 86%|########6 | 146M/170M [00:04<00:00, 34.9MB/s]
+ 88%|########8 | 150M/170M [00:04<00:00, 36.2MB/s]
+ 91%|######### | 154M/170M [00:04<00:00, 37.3MB/s]
+ 93%|#########2| 158M/170M [00:04<00:00, 36.8MB/s]
+ 95%|#########4| 161M/170M [00:04<00:00, 33.8MB/s]
+ 98%|#########7| 166M/170M [00:04<00:00, 37.4MB/s]
+100%|#########9| 170M/170M [00:05<00:00, 38.6MB/s]
+100%|##########| 170M/170M [00:05<00:00, 35.4MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -540,7 +573,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.503 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 12.875 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 5714a9a76..2bab5a423 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,7 +480,9 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 167MB/s]
+ 8%|7 | 1.06M/13.6M [00:00<00:01, 11.0MB/s]
+ 22%|##2 | 3.02M/13.6M [00:00<00:00, 16.5MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 52.7MB/s]
</pre></div>
</div>
</div>
@@ -569,7 +571,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3388 90.2751 92.1478 90.1221 0.2583
+ 90.4171 90.3343 95.6119 90.1207 0.5643
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +610,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.344 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.723 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 1d30125a5..c952e8d23 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.9834 120.9221 122.9194 119.5148 0.7500
+ 122.1707 122.0668 129.6572 120.9341 0.8749
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 0.485 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 5.507 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index f1335cdce..62787c2ae 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.662 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.686 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 3a4027938..e5096de69 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,25 +441,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5903/132723 [00:00<00:02, 59023.16KB/s]
- 10%|9 | 13168/132723 [00:00<00:01, 67033.25KB/s]
- 15%|#4 | 19872/132723 [00:00<00:01, 56776.99KB/s]
- 20%|## | 27208/132723 [00:00<00:01, 62669.29KB/s]
- 25%|##5 | 33635/132723 [00:00<00:01, 59599.78KB/s]
- 31%|### | 40880/132723 [00:00<00:01, 63610.58KB/s]
- 36%|###6 | 48253/132723 [00:00<00:01, 66729.45KB/s]
- 42%|####1 | 55646/132723 [00:00<00:01, 68929.97KB/s]
- 47%|####7 | 62945/132723 [00:00<00:00, 70161.76KB/s]
- 53%|#####2 | 70342/132723 [00:01<00:00, 71313.48KB/s]
- 59%|#####8 | 77747/132723 [00:01<00:00, 72133.14KB/s]
- 64%|######4 | 85137/132723 [00:01<00:00, 72663.22KB/s]
- 70%|######9 | 92531/132723 [00:01<00:00, 73043.23KB/s]
- 75%|#######5 | 99850/132723 [00:01<00:00, 50637.73KB/s]
- 81%|######## | 107221/132723 [00:01<00:00, 55927.99KB/s]
- 86%|########6 | 114680/132723 [00:01<00:00, 55044.71KB/s]
- 92%|#########1| 121797/132723 [00:01<00:00, 58958.44KB/s]
- 97%|#########7| 129237/132723 [00:02<00:00, 62931.15KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 63467.64KB/s]
+ 4%|3 | 5191/132723 [00:00<00:02, 51904.11KB/s]
+ 10%|9 | 12779/132723 [00:00<00:01, 65992.24KB/s]
+ 15%|#5 | 20402/132723 [00:00<00:01, 70663.44KB/s]
+ 21%|##1 | 28027/132723 [00:00<00:01, 72862.01KB/s]
+ 27%|##6 | 35737/132723 [00:00<00:01, 74385.74KB/s]
+ 33%|###2 | 43459/132723 [00:00<00:01, 75344.59KB/s]
+ 39%|###8 | 51173/132723 [00:00<00:01, 75927.36KB/s]
+ 44%|####4 | 58912/132723 [00:00<00:00, 76391.51KB/s]
+ 50%|##### | 66598/132723 [00:00<00:00, 76536.09KB/s]
+ 56%|#####6 | 74344/132723 [00:01<00:00, 76818.55KB/s]
+ 62%|######1 | 82048/132723 [00:01<00:00, 76884.60KB/s]
+ 68%|######7 | 89737/132723 [00:01<00:00, 76874.39KB/s]
+ 73%|#######3 | 97472/132723 [00:01<00:00, 77016.75KB/s]
+ 79%|#######9 | 105174/132723 [00:01<00:00, 76906.11KB/s]
+ 85%|########5 | 112877/132723 [00:01<00:00, 76940.07KB/s]
+ 91%|######### | 120572/132723 [00:01<00:00, 76613.46KB/s]
+ 97%|#########6| 128283/132723 [00:01<00:00, 76753.32KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 75419.83KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -502,7 +501,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 44.121 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 46.619 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 7a92e8ccc..17e4fc118 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:58.244</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:15.027</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:07.503</p></td>
+<td><p>03:12.875</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:44.121</p></td>
+<td><p>02:46.619</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:00.485</p></td>
+<td><p>02:05.507</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:36.662</p></td>
+<td><p>01:36.686</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:12.344</p></td>
+<td><p>01:13.723</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:30.550</p></td>
+<td><p>00:32.192</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:23.563</p></td>
+<td><p>00:23.926</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:23.010</p></td>
+<td><p>00:23.491</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 63fb14deb..5a6323fe6 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipecaa6d31-8fb0-4d0e-b2f7-b72dfe2d3677 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip110168ce-5ca5-4266-bd09-0d7497c4930b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index a4a8a0b5b..276153ded 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.379</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:44.688</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:40.094</p></td>
+<td><p>00:41.250</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.290</p></td>
+<td><p>00:02.389</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.986</p></td>
+<td><p>00:01.041</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 9ebec9919..667caa660 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7160us [7160us] (46.63%; 46.63%)
-FoldScaleAxis: 8195us [8us] (53.37%; 53.37%)
- FoldConstant: 8187us [1622us] (53.32%; 99.90%)
- InferType: 6565us [6565us] (42.76%; 80.19%)
+InferType: 7696us [7696us] (46.82%; 46.82%)
+FoldScaleAxis: 8741us [8us] (53.18%; 53.18%)
+ FoldConstant: 8733us [1815us] (53.13%; 99.91%)
+ InferType: 6918us [6918us] (42.09%; 79.22%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6646us [6646us] (44.92%; 44.92%)
-FoldScaleAxis: 8149us [7us] (55.08%; 55.08%)
- FoldConstant: 8142us [1657us] (55.03%; 99.92%)
- InferType: 6485us [6485us] (43.83%; 79.65%)
+InferType: 7161us [7161us] (45.68%; 45.68%)
+FoldScaleAxis: 8516us [7us] (54.32%; 54.32%)
+ FoldConstant: 8509us [1768us] (54.27%; 99.91%)
+ InferType: 6741us [6741us] (43.00%; 79.22%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 8b407f261..2540da89c 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 37.159966 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.219203 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index e0a3313d0..c0c04e18b 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.747671 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.059836 ms
</pre></div>
</div>
</div>
diff --git a/docs/how_to/optimize_operators/opt_gemm.html b/docs/how_to/optimize_operators/opt_gemm.html
index 6e56ae331..4e559438c 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019256
-Baseline: 3.376091
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019549
+Baseline: 3.513594
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.324201
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.332782
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.350502
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347643
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120167
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.138471
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110161
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111052
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111205
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.113193
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147490
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.149446
</pre></div>
</div>
<p>Here is the generated IR after parallelization.</p>
diff --git a/docs/how_to/optimize_operators/sg_execution_times.html b/docs/how_to/optimize_operators/sg_execution_times.html
index ad391c949..043028526 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.066</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:36.096</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.798</p></td>
+<td><p>00:33.674</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.246</p></td>
+<td><p>00:01.331</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.021</p></td>
+<td><p>00:01.092</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 45cab6885..0711a9088 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:15.886</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:27.042</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:24.362</p></td>
+<td><p>03:32.304</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:25.085</p></td>
+<td><p>01:26.596</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:48.331</p></td>
+<td><p>00:48.952</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:19.752</p></td>
+<td><p>00:20.448</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.286</p></td>
+<td><p>00:09.476</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:09.070</p></td>
+<td><p>00:09.267</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 6f5ecc1bf..579f215a3 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,12 +491,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -504,470 +504,938 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ for (rc.outer.outer: int32, 0, 16) {
+ let cse_var_2: int32 = (rc.outer.outer*1568)
+ let cse_var_1: int32 = (rc.outer.outer*288)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 17), 81)) && (floormod((threadIdx.x_1 + 17), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (floormod((threadIdx.x_1 + 4), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 21), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 25), 81)) && (floormod((threadIdx.x_1 + 25), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 46), 81)) && (floormod((threadIdx.x_1 + 46), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 16), 81)) && (floormod((threadIdx.x_1 + 16), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 33), 81)) && (floormod((threadIdx.x_1 + 33), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2058), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 33), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2254), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (floormod((threadIdx.x_1 + 3), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 20), 81)) && (floormod((threadIdx.x_1 + 20), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2450), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*73728) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 294), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 490), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 686), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 882), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1078), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 214), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1274), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 122), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1470), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 10)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1666)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1666), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 226), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1862)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1862), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 134), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2058)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2058), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 14)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2254)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2254), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 238), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2450)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2450), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 146), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2646)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2646), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 18)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2842)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2842), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 250), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3038)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3038), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 158), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3234)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3234), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 22)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3430)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3430), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 262), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3626)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3626), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 170), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3822)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3822), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 26)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4018)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4018), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 274), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4214)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4214), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 182), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4410)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4410), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 30)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 2), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4606)] = kernel[(((((blockIdx.x*73728) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 286), 288), 3)*3)) + (threadIdx.x_2 + 1)) + 69120)]
+ }
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 291)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 294)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 300)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 303)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 309)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 312)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 318)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 321)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 327)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 330)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 336)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 339)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 345)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 348)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 354)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 357)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 363)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 366)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 372)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 375)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 381)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 384)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 390)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 393)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 399)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 402)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 408)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 411)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 417)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 420)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 426)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 429)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 147)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 435)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 150)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 438)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 156)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 444)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 159)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 447)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 165)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 453)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 168)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 456)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 174)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 462)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 177)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 465)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 183)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 471)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 186)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 474)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 192)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 480)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 195)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 483)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 201)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 489)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 204)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 492)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 210)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 498)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 213)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 501)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 219)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 507)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 222)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 510)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 228)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 516)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 231)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 519)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 237)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 525)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 240)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 528)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 246)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 534)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 249)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 537)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 255)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 543)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 258)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 546)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 264)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 552)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 267)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 555)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 273)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 561)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 276)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 564)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 282)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 570)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 285)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 573)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 864)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 867)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 870)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 873)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 876)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 879)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 882)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 597)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 885)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 600)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 888)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 891)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 606)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 894)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 609)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 897)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 612)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 900)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 615)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 903)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 618)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 906)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 621)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 909)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 624)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 912)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 627)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 915)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 630)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 918)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 633)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 921)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 636)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 924)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 639)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 927)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 642)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 930)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 645)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 933)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 648)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 936)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 651)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 939)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 654)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 942)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 657)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 945)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 660)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 948)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 663)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 951)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 666)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 954)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 669)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 957)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 672)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 960)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 675)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 963)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 678)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 966)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 681)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 969)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 684)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 972)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 687)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 975)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 690)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 978)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 693)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 981)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 696)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 984)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 699)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 987)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 702)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 990)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 705)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 993)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 708)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 996)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 711)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 999)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 714)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1002)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 717)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1005)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 720)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1008)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 723)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1011)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 726)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1014)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 729)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1017)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 732)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1020)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 735)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1023)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 738)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1026)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 741)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1029)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 744)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1032)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 747)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1035)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 750)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1038)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 753)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1041)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 756)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1044)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 759)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1047)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 762)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1050)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 765)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1053)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 768)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1056)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 771)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1059)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 774)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1062)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 777)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1065)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 780)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1068)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 783)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1071)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 786)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1074)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 789)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1077)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 792)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1080)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 795)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1083)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 798)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1086)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 801)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1089)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 804)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1092)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 807)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1095)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 810)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1098)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 813)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 816)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 819)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 822)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1110)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 825)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1113)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 828)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1116)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 831)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 834)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1122)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 837)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1125)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 840)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1128)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 843)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1131)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 846)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1134)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 849)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1137)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 852)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1140)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 855)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1143)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 858)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1146)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 861)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1149)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1152)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1440)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1155)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1443)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1158)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1446)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1161)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1449)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1164)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1452)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1167)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1455)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1170)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1458)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1173)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1461)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1176)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1464)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1179)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1467)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1182)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1470)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1185)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1473)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1188)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1476)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1191)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1479)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1194)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1482)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1197)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1485)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1200)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1488)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1203)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1491)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1206)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1494)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1209)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1497)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1212)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1500)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1215)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1503)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1218)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1506)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1221)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1509)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1224)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1512)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1227)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1515)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1230)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1518)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1233)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1521)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1236)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1524)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1239)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1527)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1242)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1530)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1245)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1533)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1248)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1536)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1251)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1539)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1254)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1542)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1257)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1545)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1260)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1548)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1263)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1551)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1266)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1554)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1269)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1557)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1272)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1560)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1275)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1563)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1278)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1566)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1281)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1569)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1284)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1572)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1287)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1575)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1290)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1578)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1293)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1581)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1296)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1584)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1299)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1587)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1302)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1590)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1305)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1593)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1308)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1596)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1311)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1599)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1314)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1602)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1317)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1605)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1320)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1608)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1323)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1611)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1326)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1614)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1329)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1617)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1332)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1620)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1335)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1623)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1338)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1626)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1341)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1629)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1344)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1632)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1347)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1635)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1350)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1638)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1353)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1641)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1356)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1644)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1359)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1647)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1362)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1650)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1365)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1653)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1368)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1656)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1371)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1659)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1374)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1662)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1377)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1665)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1380)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1668)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1383)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1671)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1386)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1674)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1389)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1677)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1392)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1680)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1395)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1683)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1398)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1686)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1401)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1689)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1404)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1692)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1407)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1695)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1410)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1698)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1413)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1701)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1416)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1704)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1419)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1707)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1422)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1710)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1425)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1713)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1428)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1716)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1431)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1719)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1434)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1722)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1437)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1725)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1728)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2016)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1731)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2019)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1734)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2022)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1737)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2025)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1740)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2028)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1743)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2031)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1746)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2034)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1749)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2037)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1752)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2040)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1755)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2043)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1758)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2046)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1761)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2049)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1764)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2052)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1767)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2055)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1770)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2058)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1773)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2061)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1776)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2064)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1779)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2067)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1782)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2070)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1785)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2073)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1788)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2076)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1791)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2079)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1794)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2082)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1797)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2085)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1800)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2088)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1803)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2091)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1806)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2094)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1809)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2097)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1812)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1815)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1818)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1821)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2109)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1824)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2112)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1827)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2115)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1830)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2118)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1833)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2121)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1836)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2124)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1839)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2127)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1842)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2130)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1845)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2133)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1848)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2136)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1851)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2139)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1854)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2142)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1857)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2145)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1860)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2148)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1863)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2151)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1866)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2154)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1869)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2157)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1872)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2160)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1875)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2163)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1878)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2166)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1881)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2169)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1884)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2172)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1887)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2175)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1890)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2178)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1893)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2181)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1896)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2184)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1899)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2187)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1902)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2190)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1905)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1908)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1911)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2199)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1914)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2202)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1917)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2205)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1920)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2208)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1923)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2211)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1926)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2214)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1929)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2217)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1932)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2220)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1935)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2223)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1938)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2226)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1941)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2229)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1944)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2232)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1947)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2235)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1950)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2238)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1953)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2241)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1956)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2244)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1959)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2247)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1962)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2250)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1965)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2253)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1968)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2256)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1971)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2259)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1974)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2262)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1977)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2265)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1980)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2268)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1983)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2271)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1986)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2274)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1989)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2277)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1992)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2280)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1995)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2283)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1998)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2286)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2001)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2289)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2004)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2292)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2007)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2295)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2010)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2298)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2013)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2301)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 8) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*392)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*8)) + i1.inner)]), 0f32)
}
}
}
@@ -1004,7 +1472,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.358 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.327 ms
</pre></div>
</div>
</div>
@@ -1033,21 +1501,21 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
@@ -1055,14 +1523,14 @@ s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nc
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=8)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1082,14 +1550,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1107,10 +1575,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1119,418 +1587,861 @@ extern "C" __global__ void __launch_bounds__(64) default_function_kern
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((9 <= ((((int)threadIdx.x) + 17) % 81)) && (((((int)threadIdx.x) + 17) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((9 <= ((((int)threadIdx.x) + 4) % 81)) && (((((int)threadIdx.x) + 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 81) * 49)) + ((((((int)threadIdx.x) + 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((9 <= ((((int)threadIdx.x) + 25) % 81)) && (((((int)threadIdx.x) + 25) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + ((((((int)threadIdx.x) + 25) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((9 <= ((((int)threadIdx.x) + 46) % 81)) && (((((int)threadIdx.x) + 46) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 81) * 49)) + ((((((int)threadIdx.x) + 46) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((9 <= ((((int)threadIdx.x) + 16) % 81)) && (((((int)threadIdx.x) + 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + ((((((int)threadIdx.x) + 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((9 <= ((((int)threadIdx.x) + 33) % 81)) && (((((int)threadIdx.x) + 33) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2058) / 81) * 49)) + ((((((int)threadIdx.x) + 33) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2254) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((9 <= ((((int)threadIdx.x) + 3) % 81)) && (((((int)threadIdx.x) + 3) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + ((((((int)threadIdx.x) + 3) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((9 <= ((((int)threadIdx.x) + 20) % 81)) && (((((int)threadIdx.x) + 20) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2450) / 81) * 49)) + ((((((int)threadIdx.x) + 20) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
}
- }
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 98) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 6)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 202) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 110) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 18)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 116) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 214) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 122) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 30)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 226) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 134) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 42)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 140) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 238) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2450)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2450) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 146) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2646)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2646) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 54)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2842)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2842) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 250) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
+ kernel_shared[(((int)threadIdx.x) + 3038)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3038) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 158) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3234)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3234) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 66)];
+ kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 164) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3430)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3430) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 262) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 3626)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3626) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 170) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3822)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3822) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 78)];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4018)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4018) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 274) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
+ kernel_shared[(((int)threadIdx.x) + 4214)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4214) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 182) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4410)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4410) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 90)];
+ kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 2) {
+ kernel_shared[(((int)threadIdx.x) + 4606)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 286) / 3) * 3)) + ((int)threadIdx.x)) + 69121)];
}
+ __syncthreads();
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 288)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 291)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 294)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 297)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 300)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 303)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 306)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 309)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 312)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 315)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 318)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 321)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 324)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 327)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 330)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 333)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 336)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 339)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 342)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 345)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 348)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 351)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 354)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 357)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 360)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 363)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 366)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 369)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 372)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 375)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 378)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 381)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 384)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 387)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 390)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 393)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 396)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 399)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 402)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 405)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 408)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 411)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 414)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 417)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 420)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 423)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 426)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 429)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 432)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 147)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 435)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 150)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 438)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 153)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 441)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 156)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 444)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 159)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 447)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 162)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 450)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 165)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 453)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 168)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 456)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 171)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 459)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 174)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 462)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 177)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 465)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 180)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 468)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 183)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 471)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 186)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 474)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 189)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 477)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 192)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 480)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 195)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 483)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 198)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 486)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 201)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 489)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 204)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 492)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 207)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 495)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 210)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 498)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 213)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 501)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 216)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 504)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 219)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 507)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 222)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 510)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 513)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 228)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 516)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 231)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 519)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 234)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 522)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 237)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 525)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 240)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 528)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 243)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 531)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 246)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 534)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 249)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 537)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 252)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 540)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 255)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 543)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 258)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 546)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 261)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 549)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 264)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 552)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 267)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 555)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 270)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 558)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 273)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 561)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 276)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 564)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 279)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 567)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 282)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 570)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 285)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 573)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 864)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 867)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 870)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 873)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 876)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 879)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 882)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 597)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 885)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 600)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 888)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 891)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 606)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 894)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 609)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 897)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 612)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 900)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 615)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 903)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 618)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 906)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 621)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 909)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 624)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 912)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 627)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 915)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 630)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 918)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 633)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 921)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 636)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 924)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 639)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 927)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 642)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 930)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 645)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 933)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 648)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 936)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 651)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 939)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 654)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 942)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 657)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 945)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 660)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 948)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 663)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 951)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 666)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 954)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 669)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 957)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 672)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 960)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 675)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 963)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 678)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 966)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 681)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 969)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 684)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 972)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 687)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 975)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 690)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 978)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 693)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 981)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 696)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 984)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 699)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 987)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 702)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 990)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 705)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 993)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 708)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 996)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 711)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 999)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 714)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1002)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 717)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1005)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 720)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1008)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 723)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1011)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 726)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1014)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 729)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1017)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 732)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1020)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 735)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1023)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 738)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1026)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 741)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1029)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 744)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1032)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 747)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1035)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 750)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1038)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 753)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1041)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 756)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1044)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 759)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1047)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 762)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1050)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 765)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1053)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 768)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1056)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 771)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1059)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 774)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1062)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 777)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1065)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 780)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1068)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 783)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1071)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 786)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1074)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 789)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1077)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 792)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1080)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 795)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1083)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 798)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1086)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 801)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1089)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 804)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1092)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 807)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1095)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 810)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1098)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 813)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 816)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 819)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 822)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1110)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 825)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1113)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 828)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1116)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 831)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 834)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1122)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 837)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1125)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 840)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1128)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 843)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1131)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 846)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1134)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 849)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1137)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 852)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1140)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 855)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1143)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 858)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1146)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 861)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1149)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1152)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1440)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1155)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1443)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1158)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1446)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1161)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1449)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1164)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1452)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1167)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1455)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1170)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1458)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1173)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1461)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1176)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1464)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1179)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1467)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1182)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1470)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1185)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1473)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1188)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1476)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1191)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1479)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1194)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1482)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1197)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1485)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1200)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1488)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1203)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1491)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1206)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1494)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1209)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1497)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1212)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1500)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1215)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1503)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1218)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1506)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1221)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1509)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1224)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1512)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1227)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1515)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1230)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1518)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1233)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1521)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1236)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1524)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1239)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1527)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1242)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1530)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1245)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1533)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1248)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1536)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1251)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1539)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1254)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1542)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1257)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1545)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1260)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1548)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1263)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1551)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1266)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1554)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1269)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1557)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1272)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1560)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1275)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1563)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1278)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1566)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1281)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1569)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1284)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1572)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1287)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1575)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1290)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1293)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1296)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1299)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1302)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1590)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1305)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1593)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1308)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1596)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1311)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1599)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1314)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1602)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1317)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1605)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1320)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1608)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1323)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1611)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1326)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1614)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1329)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1617)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1332)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1620)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1335)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1623)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1338)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1626)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1341)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1629)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1344)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1632)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1347)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1635)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1350)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1638)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1353)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1641)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1356)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1644)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1359)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1647)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1362)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1650)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1365)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1653)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1368)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1656)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1371)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1659)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1374)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1662)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1377)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1665)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1380)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1668)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1383)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1671)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1386)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1674)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1389)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1677)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1392)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1680)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1395)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1683)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1398)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1686)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1401)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1689)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1404)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1692)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1407)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1695)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1410)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1698)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1413)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1701)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1416)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1704)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1419)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1707)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1422)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1710)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1425)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1713)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1428)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1716)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1431)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1719)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1434)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1722)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1437)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1725)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1728)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2016)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1731)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2019)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1734)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2022)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1737)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2025)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1740)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2028)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1743)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2031)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1746)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2034)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1749)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2037)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1752)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2040)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1755)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2043)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1758)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2046)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1761)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2049)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1764)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2052)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1767)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2055)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1770)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2058)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1773)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2061)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1776)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2064)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1779)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2067)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1782)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2070)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1785)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2073)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1788)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2076)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1791)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2079)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1794)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2082)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1797)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2085)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1800)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2088)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1803)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2091)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1806)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2094)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1809)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2097)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1812)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1815)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1818)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1821)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2109)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1824)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2112)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1827)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2115)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1830)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2118)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1833)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2121)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1836)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2124)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1839)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2127)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1842)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2130)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1845)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2133)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1848)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2136)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1851)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2139)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1854)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2142)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1857)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2145)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1860)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2148)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1863)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2151)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1866)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2154)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1869)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2157)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1872)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2160)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1875)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2163)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1878)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2166)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1881)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2169)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1884)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2172)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1887)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2175)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1890)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2178)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1893)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2181)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1896)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2184)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1899)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2187)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1902)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2190)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1905)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1908)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1911)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2199)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1914)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2202)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1917)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2205)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1920)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2208)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1923)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2211)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1926)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2214)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1929)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2217)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1932)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2220)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1935)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2223)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1938)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2226)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1941)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2229)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1944)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2232)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1947)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2235)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1950)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2238)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1953)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2241)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1956)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2244)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1959)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2247)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1962)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2250)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1965)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2253)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1968)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2256)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1971)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2259)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1974)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2262)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1977)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2265)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1980)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2268)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1983)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2271)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1986)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2274)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1989)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2277)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1992)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2280)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1995)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2283)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1998)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2286)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2001)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2289)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2004)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2292)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2007)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2295)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2010)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2298)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2013)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2301)]));
+ }
+ }
+ for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 8)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1567,7 +2478,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 24.362 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 32.304 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index d57b8a98b..25fda6126 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.9072 9.9166 9.9443 9.8609 0.0347
+ 10.1722 10.1849 10.2133 10.1185 0.0397
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index d12fa6a4a..152be884e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 759.7426 759.4176 760.5847 759.2257 0.6005
+ 768.7073 768.2559 770.1201 767.7458 1.0205
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.085 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.596 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index e79fb7e04..155a95613 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,14 +625,14 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 4) {
- let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
{
- compute_5: Buffer(compute_4, float32, [256], [])[cse_var_1] = 0f32
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
compute_5[(cse_var_1 + 2)] = 0f32
compute_5[(cse_var_1 + 3)] = 0f32
@@ -650,53 +650,80 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 4) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = floordiv(floormod(i0.outer.i1.outer.fused, 64), 2)
- let cse_var_19: int32 = ((i.outer.inner*64) + (i.inner*16))
- let cse_var_18: int32 = (cse_var_19 + 9)
- let cse_var_17: int32 = (cse_var_19 + 8)
- let cse_var_16: int32 = (cse_var_19 + 7)
- let cse_var_15: int32 = (cse_var_19 + 6)
- let cse_var_14: int32 = (cse_var_19 + 5)
- let cse_var_13: int32 = (cse_var_19 + 4)
- let cse_var_12: int32 = (cse_var_19 + 3)
- let cse_var_11: int32 = (cse_var_19 + 2)
- let cse_var_10: int32 = (cse_var_19 + 15)
- let cse_var_9: int32 = (cse_var_19 + 14)
- let cse_var_8: int32 = (cse_var_19 + 13)
- let cse_var_7: int32 = (cse_var_19 + 12)
- let cse_var_6: int32 = (cse_var_19 + 11)
- let cse_var_5: int32 = (cse_var_19 + 10)
- let cse_var_4: int32 = (cse_var_19 + 1)
- let cse_var_3: int32 = (((floordiv(i0.outer.i1.outer.fused, 64)*4096) + (i.outer.inner*1024)) + (i.inner*256))
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
+ for (i.inner: int32, 0, 32) {
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ }
+ if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
+ let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_23: int32 = floormod(i0.outer.i1.outer.fused, 64)
- let cse_var_24: int32 = (cse_var_23*8)
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 64)*8192) + (i0.inner*512)) + cse_var_24)
- compute[ramp(cse_var_22, 1, 8)] = max((compute_5[ramp((((i0.inner*16) + cse_var_24) - (floordiv(cse_var_23, 2)*16)), 1, 8)] + placeholder_4[ramp(cse_var_22, 1, 8)]), broadcast(0f32, 8))
+ for (i0.inner: int32, 0, 128) {
+ for (i1.inner: int32, 0, 16) {
+ let cse_var_18: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
+ compute[cse_var_18] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_18]), 0f32)
+ }
}
}
}
@@ -734,7 +761,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 4.554 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.812 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/sg_execution_times.html b/docs/how_to/tune_with_autotvm/sg_execution_times.html
index 2c66c5df1..12c9dcd39 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.635</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.884</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.595</p></td>
+<td><p>00:46.847</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.024</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 00fb5fede..dca82bd73 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 220.00/220.00 result: MeasureResult(costs=(0.0010522569862068964,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9134447574615479, timestamp=1662069506.9271834) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/220.00 result: Traceback (most recent call last):
+No: 9 GFLOPS: 179.14/179.14 result: MeasureResult(costs=(0.0012922816555555555,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1458566188812256, timestamp=1662088041.091059) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/179.14 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.86/260.86 result: MeasureResult(costs=(0.0008874624143646408,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.821462631225586, timestamp=1662069507.8597355) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.81/260.81 result: MeasureResult(costs=(0.0008876353535911603,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4380462169647217, timestamp=1662088041.955188) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.27/260.86 result: MeasureResult(costs=(0.04389160225,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9344241619110107, timestamp=1662069512.5662534) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.35/260.86 result: MeasureResult(costs=(0.0692019565,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.679275751113892, timestamp=1662069513.8073626) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.29/260.81 result: MeasureResult(costs=(0.04375010175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8807947635650635, timestamp=1662088046.6638134) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.36/260.81 result: MeasureResult(costs=(0.0689354325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.713005542755127, timestamp=1662088047.9242866) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.08/260.86 result: MeasureResult(costs=(0.008243709785714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.303654670715332, timestamp=1662069524.8603585) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.09/260.81 result: MeasureResult(costs=(0.0082418215,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3147664070129395, timestamp=1662088058.9725747) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.86 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001284
+Time cost of this operator: 0.001265
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 4e69e5227..14246b2c8 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.4 98.722 (1, 2, 10, 10, 3) 2 1 [311.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.066 0.972 (1, 6, 10, 10) 1 1 [3.066]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 0.306 (1, 1, 10, 10, 3) 1 1 [0.965]
-Total_time - 315.432 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.1 98.705 (1, 2, 10, 10, 3) 2 1 [312.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.093 0.978 (1, 6, 10, 10) 1 1 [3.093]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.003 0.317 (1, 1, 10, 10, 3) 1 1 [1.003]
+Total_time - 316.196 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 207.9 98.765 (1, 6, 10, 10, 1) 2 1 [207.9]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.757 0.835 (1, 6, 10, 10) 1 1 [1.757]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.843 0.401 (1, 3, 10, 10, 1) 1 1 [0.843]
-Total_time - 210.501 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.562 96.441 (1, 6, 10, 10, 1) 2 1 [81.562]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.002 2.367 (1, 6, 10, 10) 1 1 [2.002]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.008 1.192 (1, 1, 10, 10, 3) 1 1 [1.008]
+Total_time - 84.572 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 91a9dc4c2..7bd21512b 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp6s63bl_j/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp1er51kvn/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp6s63bl_j/images/target contains 8144 images
-/tmp/tmp6s63bl_j/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp1er51kvn/images/target contains 8144 images
+/tmp/tmp1er51kvn/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 56s - loss: 0.2142 - accuracy: 0.9277 - val_loss: 0.1467 - val_accuracy: 0.9573
+328/328 - 57s - loss: 0.2074 - accuracy: 0.9304 - val_loss: 0.1327 - val_accuracy: 0.9585
Epoch 2/3
-328/328 - 53s - loss: 0.0970 - accuracy: 0.9647 - val_loss: 0.1137 - val_accuracy: 0.9675
+328/328 - 53s - loss: 0.0980 - accuracy: 0.9621 - val_loss: 0.1232 - val_accuracy: 0.9619
Epoch 3/3
-328/328 - 53s - loss: 0.0685 - accuracy: 0.9749 - val_loss: 0.1283 - val_accuracy: 0.9641
+328/328 - 53s - loss: 0.0659 - accuracy: 0.9757 - val_loss: 0.1522 - val_accuracy: 0.9490
-<keras.callbacks.History object at 0x7f68e3fac2d0>
+<keras.callbacks.History object at 0x7f820c1c4850>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 19.302 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 46.419 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 215261299..7580ad38d 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:14.890</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:43.632</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:19.302</p></td>
+<td><p>04:46.419</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:44.009</p></td>
+<td><p>00:45.532</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.114</p></td>
+<td><p>00:08.076</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.463</p></td>
+<td><p>00:03.603</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 535748352..c4d26b4de 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.290</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:44.891</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.504</p></td>
+<td><p>00:33.679</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.250</p></td>
+<td><p>00:09.618</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.529</p></td>
+<td><p>00:01.586</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index d820ab50e..93d6ad6be 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f68d83f55f0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f81dc1bedd0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index e5712b5d5..1466ed20c 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.299</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.481</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.987</p></td>
+<td><p>00:02.077</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.043</p></td>
+<td><p>00:01.068</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.545</p></td>
+<td><p>00:00.574</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.531</p></td>
+<td><p>00:00.564</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.106</p></td>
+<td><p>00:00.107</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.042</p></td>
+<td><p>00:00.045</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 783583357..8385a97d0 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp4uwwt9p5/input0.cc'\nsource_filename = \"/tmp/tmp4uwwt9p5/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjevgenwl/input0.cc'\nsource_filename = \"/tmp/tmpjevgenwl/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/doxygen/c__backend__api_8h_source.html b/docs/reference/api/doxygen/c__backend__api_8h_source.html
index de38d7da2..400068a31 100644
--- a/docs/reference/api/doxygen/c__backend__api_8h_source.html
+++ b/docs/reference/api/doxygen/c__backend__api_8h_source.html
@@ -66,13 +66,13 @@ $(function() {
<div class="title">c_backend_api.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="c__backend__api_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
+<a href="c__backend__api_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
<div class="ttc" id="c__backend__api_8h_html_a56a654a9aeba2f1ccf3e10918dd88ec5"><div class="ttname"><a href="c__backend__api_8h.html#a56a654a9aeba2f1ccf3e10918dd88ec5">TVMBackendGetFuncFromEnv</a></div><div class="ttdeci">int TVMBackendGetFuncFromEnv(void *mod_node, const char *func_name, TVMFunctionHandle *out)</div><div class="ttdoc">Backend function for modules to get function from its environment mod_node (its imports and global fu...</div></div>
<div class="ttc" id="c__backend__api_8h_html_ae70bd3ee026eb55b438ada05b08f0ce8"><div class="ttname"><a href="c__backend__api_8h.html#ae70bd3ee026eb55b438ada05b08f0ce8">TVMBackendRunOnce</a></div><div class="ttdeci">int TVMBackendRunOnce(void **handle, int(*f)(void *), void *cdata, int nbytes)</div><div class="ttdoc">Simple static initialization function. Run f once and set handle to be not null. This function is mai...</div></div>
<div class="ttc" id="c__backend__api_8h_html_a07eaf7d1b748d99aa7715c7adbdea231"><div class="ttname"><a href="c__backend__api_8h.html#a07eaf7d1b748d99aa7715c7adbdea231">TVMBackendAllocWorkspace</a></div><div class="ttdeci">void * TVMBackendAllocWorkspace(int device_type, int device_id, uint64_t nbytes, int dtype_code_hint, int dtype_bits_hint)</div><div class="ttdoc">Backend function to allocate temporal workspace. </div></div>
<div class="ttc" id="unionTVMValue_html"><div class="ttname"><a href="unionTVMValue.html">TVMValue</a></div><div class="ttdoc">Union type of values being passed through API and function calls. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:144</div></div>
<div class="ttc" id="structTVMParallelGroupEnv_html"><div class="ttname"><a href="structTVMParallelGroupEnv.html">TVMParallelGroupEnv</a></div><div class="ttdoc">Environment for TVM parallel task. </div><div class="ttdef"><b>Definition:</b> c_backend_api.h:119</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a61b1ef1047fb722a4e5ec2167c9963d7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a61b1ef1047fb722a4e5ec2167c9963d7">tvm::tir::attr::device_id</a></div><div class="ttdeci">constexpr const char * device_id</div><div class="ttdoc">The allocation device for global malloc in host. </div><div class="ttdef"><b>Definition:</b> stmt.h:1389</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a61b1ef1047fb722a4e5ec2167c9963d7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a61b1ef1047fb722a4e5ec2167c9963d7">tvm::tir::attr::device_id</a></div><div class="ttdeci">constexpr const char * device_id</div><div class="ttdoc">The allocation device for global malloc in host. </div><div class="ttdef"><b>Definition:</b> stmt.h:1390</div></div>
<div class="ttc" id="c__runtime__api_8h_html_acf57d257a6e0841d84ebbd2a339d183e"><div class="ttname"><a href="c__runtime__api_8h.html#acf57d257a6e0841d84ebbd2a339d183e">TVMFunctionHandle</a></div><div class="ttdeci">void * TVMFunctionHandle</div><div class="ttdoc">Handle to packed function handle. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:165</div></div>
<div class="ttc" id="c__backend__api_8h_html_a6ff8662943d0f003d55d9046cd24daf8"><div class="ttname"><a href="c__backend__api_8h.html#a6ff8662943d0f003d55d9046cd24daf8">TVMBackendParallelLaunch</a></div><div class="ttdeci">int TVMBackendParallelLaunch(FTVMParallelLambda flambda, void *cdata, int num_task)</div><div class="ttdoc">Backend function for running parallel jobs. </div></div>
<div class="ttc" id="c__backend__api_8h_html_a0c57deb5acb9338ec778d91bd6e42191"><div class="ttname"><a href="c__backend__api_8h.html#a0c57deb5acb9338ec778d91bd6e42191">TVMBackendRegisterSystemLibSymbol</a></div><div class="ttdeci">int TVMBackendRegisterSystemLibSymbol(const char *name, void *ptr)</div><div class="ttdoc">Backend function to register system-wide library symbol. </div></div>
diff --git a/docs/reference/api/doxygen/c__runtime__api_8h_source.html b/docs/reference/api/doxygen/c__runtime__api_8h_source.html
index 4412981ec..c9f2c0502 100644
--- a/docs/reference/api/doxygen/c__runtime__api_8h_source.html
+++ b/docs/reference/api/doxygen/c__runtime__api_8h_source.html
@@ -70,7 +70,7 @@ $(function() {
<div class="ttc" id="unionTVMValue_html_aa1c40fa9e74fbf97541fd9735062c4cc"><div class="ttname"><a href="unionTVMValue.html#aa1c40fa9e74fbf97541fd9735062c4cc">TVMValue::v_int64</a></div><div class="ttdeci">int64_t v_int64</div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:145</div></div>
<div class="ttc" id="c__runtime__api_8h_html_a07954203342f2787acf988c4c351d9c3"><div class="ttname"><a href="c__runtime__api_8h.html#a07954203342f2787acf988c4c351d9c3">TVMPackedCFunc</a></div><div class="ttdeci">int(* TVMPackedCFunc)(TVMValue *args, int *type_codes, int num_args, TVMRetValueHandle ret, void *resource_handle)</div><div class="ttdoc">C type of packed function. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:305</div></div>
<div class="ttc" id="c__runtime__api_8h_html_a477111f9accd70633dc5f2e7139b6cf4"><div class="ttname"><a href="c__runtime__api_8h.html#a477111f9accd70633dc5f2e7139b6cf4">TVMAPISetLastError</a></div><div class="ttdeci">void TVMAPISetLastError(const char *msg)</div><div class="ttdoc">Used for implementing C API function. Set last error message before return. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a7e4e7cd47471a9089022214d63d24206"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a7e4e7cd47471a9089022214d63d24206">tvm::tir::attr::device_type</a></div><div class="ttdeci">constexpr const char * device_type</div><div class="ttdoc">The device type. </div><div class="ttdef"><b>Definition:</b> stmt.h:1391</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a7e4e7cd47471a9089022214d63d24206"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a7e4e7cd47471a9089022214d63d24206">tvm::tir::attr::device_type</a></div><div class="ttdeci">constexpr const char * device_type</div><div class="ttdoc">The device type. </div><div class="ttdef"><b>Definition:</b> stmt.h:1392</div></div>
<div class="ttc" id="c__runtime__api_8h_html_af420f0d74004615c03bb40270ad5d489"><div class="ttname"><a href="c__runtime__api_8h.html#af420f0d74004615c03bb40270ad5d489">TVMFuncFree</a></div><div class="ttdeci">int TVMFuncFree(TVMFunctionHandle func)</div><div class="ttdoc">Free the function when it is no longer needed. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_a591e48e52098965e235657dab56bc096"><div class="ttname"><a href="c__runtime__api_8h.html#a591e48e52098965e235657dab56bc096">TVMArrayFree</a></div><div class="ttdeci">int TVMArrayFree(TVMArrayHandle handle)</div><div class="ttdoc">Free the TVM Array. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_a57cbccb14c35a0e62dbc1b911188fcefacdc33f5efa9ddabe89e886c28d1ff65b"><div class="ttname"><a href="c__runtime__api_8h.html#a57cbccb14c35a0e62dbc1b911188fcefacdc33f5efa9ddabe89e886c28d1ff65b">kDLSDAccel</a></div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:86</div></div>
@@ -102,7 +102,7 @@ $(function() {
<div class="ttc" id="c__runtime__api_8h_html_a8a01e20ffd5784465df0759c950154b5"><div class="ttname"><a href="c__runtime__api_8h.html#a8a01e20ffd5784465df0759c950154b5">TVMFuncCall</a></div><div class="ttdeci">int TVMFuncCall(TVMFunctionHandle func, TVMValue *arg_values, int *type_codes, int num_args, TVMValue *ret_val, int *ret_type_code)</div><div class="ttdoc">Call a Packed TVM Function. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_aa91f776ed41a36790409f78725f81419"><div class="ttname"><a href="c__runtime__api_8h.html#aa91f776ed41a36790409f78725f81419">TVMStreamStreamSynchronize</a></div><div class="ttdeci">int TVMStreamStreamSynchronize(int device_type, int device_id, TVMStreamHandle src, TVMStreamHandle dst)</div><div class="ttdoc">Synchronize two streams of execution. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_a6fee438ab81fbf4235375d9f17f36d6f"><div class="ttname"><a href="c__runtime__api_8h.html#a6fee438ab81fbf4235375d9f17f36d6f">TVMCbArgToReturn</a></div><div class="ttdeci">int TVMCbArgToReturn(TVMValue *value, int *code)</div><div class="ttdoc">Inplace translate callback argument value to return value. This is only needed for non-POD arguments...</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a61b1ef1047fb722a4e5ec2167c9963d7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a61b1ef1047fb722a4e5ec2167c9963d7">tvm::tir::attr::device_id</a></div><div class="ttdeci">constexpr const char * device_id</div><div class="ttdoc">The allocation device for global malloc in host. </div><div class="ttdef"><b>Definition:</b> stmt.h:1389</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a61b1ef1047fb722a4e5ec2167c9963d7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a61b1ef1047fb722a4e5ec2167c9963d7">tvm::tir::attr::device_id</a></div><div class="ttdeci">constexpr const char * device_id</div><div class="ttdoc">The allocation device for global malloc in host. </div><div class="ttdef"><b>Definition:</b> stmt.h:1390</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ab98d6b66089da8b33b662ccdb243b26b"><div class="ttname"><a href="c__runtime__api_8h.html#ab98d6b66089da8b33b662ccdb243b26b">TVMFuncRemoveGlobal</a></div><div class="ttdeci">int TVMFuncRemoveGlobal(const char *name)</div><div class="ttdoc">Remove a global function. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_a57cbccb14c35a0e62dbc1b911188fcefaad7f2a6159af2f349840446d850f1402"><div class="ttname"><a href="c__runtime__api_8h.html#a57cbccb14c35a0e62dbc1b911188fcefaad7f2a6159af2f349840446d850f1402">kDLHexagon</a></div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:89</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ad3bd42da244a0e32ac82d7428e01a010"><div class="ttname"><a href="c__runtime__api_8h.html#ad3bd42da244a0e32ac82d7428e01a010">TVMFuncGetGlobal</a></div><div class="ttdeci">int TVMFuncGetGlobal(const char *name, TVMFunctionHandle *out)</div><div class="ttdoc">Get a global function. </div></div>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html
index d92ac4862..91ec6a004 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database-members.html
@@ -90,10 +90,12 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a3deeeac5827a88f375b8c6ae1039c219">operator-></a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4744bf4a1b48f202d41b51dc5e08e6ee">operator<</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#affdf1b8cdb36e140de7b3ad7064e4617">operator==</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae81f559342e4628ea1bffce6db36e547">PyDatabase</a>(PyDatabaseNode::FHasWorkload f_has_workload, PyDatabaseNode::FCommitWorkload f_commit_workload, PyDatabaseNode::FCommitTuningRecord f_commit_tuning_record, PyDatabaseNode::FGetTopK f_get_top_k, PyDatabaseNode::FGetAllTuningRecords f_get_all_tuning_records, PyDatabaseNode::FSize f_size)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedul [...]
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#ae31a5b9f40781d60a2901994ead700e8">same_as</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4">ScheduleFnDatabase</a>(runtime::TypedPackedFunc< bool(tir::Schedule)> schedule_fn)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afb40a32e35f299ee0c6cd6f99f1ed44a">TVM_DEFINE_MUTABLE_NOTNULLABLE_OBJECT_REF_METHODS</a>(Database, runtime::ObjectRef, DatabaseNode)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae4f6e0e951be446d2ab836eb8a9bcc83">OrderedUnionDatabase</a>(Array< Database, void > databases)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae81f559342e4628ea1bffce6db36e547">PyDatabase</a>(PyDatabaseNode::FHasWorkload f_has_workload, PyDatabaseNode::FCommitWorkload f_commit_workload, PyDatabaseNode::FCommitTuningRecord f_commit_tuning_record, PyDatabaseNode::FGetTopK f_get_top_k, PyDatabaseNode::FGetAllTuningRecords f_get_all_tuning_records, PyDatabaseNode::FSize f_size)</td><td class="entry"><a class="el" href="classtvm_1_1 [...]
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#ae31a5b9f40781d60a2901994ead700e8">same_as</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afd3cddb62e6fad7974e457b708c895a4">ScheduleFnDatabase</a>(runtime::TypedPackedFunc< bool(tir::Schedule)> schedule_fn)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#afb40a32e35f299ee0c6cd6f99f1ed44a">TVM_DEFINE_MUTABLE_NOTNULLABLE_OBJECT_REF_METHODS</a>(Database, runtime::ObjectRef, DatabaseNode)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#affcd4ddc4911a83f281de558366a6d63">UnionDatabase</a>(Array< Database, void > databases)</td><td class="entry"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">tvm::meta_schedule::Database</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a0ae0da21d247cd87ea94fe3777c4405e">use_count</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
</table></div><!-- contents -->
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html
index 4e159658a..8dd3a439c 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database.html
@@ -78,13 +78,13 @@ $(function() {
<div class="dynheader">
Inheritance diagram for tvm::meta_schedule::Database:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg" width="198" height="595"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg" width="210" height="624"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<div class="dynheader">
Collaboration diagram for tvm::meta_schedule::Database:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__coll__graph.svg" width="198" height="883"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1meta__schedule_1_1Database__coll__graph.svg" width="210" height="912"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<table class="memberdecls">
@@ -142,6 +142,12 @@ Static Public Member Functions</h2></td></tr>
<tr class="memitem:a9eba4e789ead8b3ffd53280390660d1e"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#a9eba4e789ead8b3ffd53280390660d1e">JSONDatabase</a> (<a class="el" href="classtvm_1_1runtime_1_1String.html">String</a> path_workload, <a class="el" href="classtvm_1_1runtime_1_1String.ht [...]
<tr class="memdesc:a9eba4e789ead8b3ffd53280390660d1e"><td class="mdescLeft"> </td><td class="mdescRight">Create a default database that uses JSON file for tuning records. <a href="#a9eba4e789ead8b3ffd53280390660d1e">More...</a><br /></td></tr>
<tr class="separator:a9eba4e789ead8b3ffd53280390660d1e"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:affcd4ddc4911a83f281de558366a6d63"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#affcd4ddc4911a83f281de558366a6d63">UnionDatabase</a> (<a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html" [...]
+<tr class="memdesc:affcd4ddc4911a83f281de558366a6d63"><td class="mdescLeft"> </td><td class="mdescRight">A database composed of multiple databases, allowing users to guide IR rewriting using combined knowledge of those databases. To each query, it returns the best record among all the databases given. <a href="#affcd4ddc4911a83f281de558366a6d63">More...</a><br /></td></tr>
+<tr class="separator:affcd4ddc4911a83f281de558366a6d63"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ae4f6e0e951be446d2ab836eb8a9bcc83"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae4f6e0e951be446d2ab836eb8a9bcc83">OrderedUnionDatabase</a> (<a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1Databas [...]
+<tr class="memdesc:ae4f6e0e951be446d2ab836eb8a9bcc83"><td class="mdescLeft"> </td><td class="mdescRight">A database composed of multiple databases, allowing users to guide IR rewriting using combined knowledge of those databases. To each query, it returns the record from the first database that responds to the query. <a href="#ae4f6e0e951be446d2ab836eb8a9bcc83">More...</a><br /></td></tr>
+<tr class="separator:ae4f6e0e951be446d2ab836eb8a9bcc83"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:ae81f559342e4628ea1bffce6db36e547"><td class="memItemLeft" align="right" valign="top">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae81f559342e4628ea1bffce6db36e547">PyDatabase</a> (<a class="el" href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#afb177ebca29227e94c3b3036b4908bad">PyDatabaseNode::FHasWorkload</a [...]
<tr class="memdesc:ae81f559342e4628ea1bffce6db36e547"><td class="mdescLeft"> </td><td class="mdescRight">Create a database with customized methods on the python-side. <a href="#ae81f559342e4628ea1bffce6db36e547">More...</a><br /></td></tr>
<tr class="separator:ae81f559342e4628ea1bffce6db36e547"><td class="memSeparator" colspan="2"> </td></tr>
@@ -321,6 +327,41 @@ Additional Inherited Members</h2></td></tr>
</div><div class="memdoc">
<p>An in-memory database. </p>
+</div>
+</div>
+<a id="ae4f6e0e951be446d2ab836eb8a9bcc83"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ae4f6e0e951be446d2ab836eb8a9bcc83">◆ </a></span>OrderedUnionDatabase()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> tvm::meta_schedule::Database::OrderedUnionDatabase </td>
+ <td>(</td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a>, void > </td>
+ <td class="paramname"><em>databases</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">static</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>A database composed of multiple databases, allowing users to guide IR rewriting using combined knowledge of those databases. To each query, it returns the record from the first database that responds to the query. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">databases</td><td>The database to be subsetted. </td></tr>
+ </table>
+ </dd>
+</dl>
+<dl class="section return"><dt>Returns</dt><dd>The subsetted database. </dd></dl>
+
</div>
</div>
<a id="ae81f559342e4628ea1bffce6db36e547"></a>
@@ -463,6 +504,41 @@ Additional Inherited Members</h2></td></tr>
</table>
</div><div class="memdoc">
+</div>
+</div>
+<a id="affcd4ddc4911a83f281de558366a6d63"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#affcd4ddc4911a83f281de558366a6d63">◆ </a></span>UnionDatabase()</h2>
+
+<div class="memitem">
+<div class="memproto">
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">static <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a> tvm::meta_schedule::Database::UnionDatabase </td>
+ <td>(</td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Array.html">Array</a>< <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html">Database</a>, void > </td>
+ <td class="paramname"><em>databases</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">static</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
+<p>A database composed of multiple databases, allowing users to guide IR rewriting using combined knowledge of those databases. To each query, it returns the best record among all the databases given. </p>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">databases</td><td>The list of databases to be combined. </td></tr>
+ </table>
+ </dd>
+</dl>
+<dl class="section return"><dt>Returns</dt><dd>The combined database. </dd></dl>
+
</div>
</div>
<hr/>The documentation for this class was generated from the following file:<ul>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg
index 7076f6710..b89b2cb69 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__coll__graph.svg
@@ -4,28 +4,30 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::meta_schedule::Database Pages: 1 -->
-<svg width="148pt" height="662pt"
- viewBox="0.00 0.00 148.00 662.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 658)">
+<svg width="157pt" height="684pt"
+ viewBox="0.00 0.00 157.00 684.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 680)">
<title>tvm::meta_schedule::Database</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-658 144,-658 144,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-680 153,-680 153,4 -4,4"/>
<!-- Node2 -->
<g id="node1" class="node">
<title>Node2</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-167.5 140,-167.5 140,-.5 0,-.5"/>
-<text text-anchor="start" x="8" y="-155.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="70" y="-144.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
-<polyline fill="none" stroke="#000000" points="0,-137.5 140,-137.5 "/>
-<text text-anchor="middle" x="70" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-118.5 140,-118.5 "/>
-<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
-<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
-<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
-<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
-<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ScheduleFnDatabase()</text>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ JSONDatabase()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-189.5 149,-189.5 149,-.5 0,-.5"/>
+<text text-anchor="start" x="8" y="-177.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="74.5" y="-166.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
+<polyline fill="none" stroke="#000000" points="0,-159.5 149,-159.5 "/>
+<text text-anchor="middle" x="74.5" y="-147.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-140.5 149,-140.5 "/>
+<text text-anchor="start" x="8" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
+<text text-anchor="start" x="8" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
+<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ScheduleFnDatabase()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ JSONDatabase()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ UnionDatabase()</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ OrderedUnionDatabase()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PyDatabase()</text>
<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Current()</text>
</g>
@@ -33,66 +35,66 @@
<g id="node2" class="node">
<title>Node3</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="3,-205.5 3,-427.5 137,-427.5 137,-205.5 3,-205.5"/>
-<text text-anchor="middle" x="70" y="-415.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="3,-408.5 137,-408.5 "/>
-<text text-anchor="start" x="11" y="-396.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="3,-389.5 137,-389.5 "/>
-<text text-anchor="start" x="11" y="-377.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-366.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-355.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="11" y="-344.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="11" y="-333.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="11" y="-322.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="11" y="-311.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="11" y="-300.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="11" y="-289.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="11" y="-278.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="11" y="-267.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="11" y="-256.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="11" y="-245.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="11" y="-234.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="11" y="-223.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="11" y="-212.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="7.5,-227.5 7.5,-449.5 141.5,-449.5 141.5,-227.5 7.5,-227.5"/>
+<text text-anchor="middle" x="74.5" y="-437.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="7.5,-430.5 141.5,-430.5 "/>
+<text text-anchor="start" x="15.5" y="-418.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="7.5,-411.5 141.5,-411.5 "/>
+<text text-anchor="start" x="15.5" y="-399.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="15.5" y="-388.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="15.5" y="-377.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="15.5" y="-366.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="15.5" y="-355.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="15.5" y="-344.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="15.5" y="-333.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="15.5" y="-322.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="15.5" y="-311.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="15.5" y="-300.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="15.5" y="-289.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="15.5" y="-278.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="15.5" y="-267.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="15.5" y="-256.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="15.5" y="-245.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="15.5" y="-234.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node3->Node2 -->
<g id="edge1" class="edge">
<title>Node3->Node2</title>
-<path fill="none" stroke="#191970" d="M70,-195.2104C70,-185.8646 70,-176.5624 70,-167.5459"/>
-<polygon fill="none" stroke="#191970" points="66.5001,-195.3571 70,-205.3572 73.5001,-195.3572 66.5001,-195.3571"/>
+<path fill="none" stroke="#191970" d="M74.5,-217.3207C74.5,-207.9853 74.5,-198.6454 74.5,-189.5206"/>
+<polygon fill="none" stroke="#191970" points="71.0001,-217.4384 74.5,-227.4384 78.0001,-217.4385 71.0001,-217.4384"/>
</g>
<!-- Node4 -->
<g id="node3" class="node">
<title>Node4</title>
<g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\< tvm::runtime::Object \>\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator-\>()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="0,-475.5 0,-653.5 140,-653.5 140,-475.5 0,-475.5"/>
-<text text-anchor="start" x="8" y="-641.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="70" y="-630.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
-<polyline fill="none" stroke="#000000" points="0,-623.5 140,-623.5 "/>
-<text text-anchor="middle" x="70" y="-611.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-604.5 140,-604.5 "/>
-<text text-anchor="start" x="8" y="-592.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-581.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-570.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-559.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-548.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-537.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-526.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="8" y="-515.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="8" y="-504.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="8" y="-493.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="8" y="-482.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<polygon fill="#ffffff" stroke="#000000" points="4.5,-497.5 4.5,-675.5 144.5,-675.5 144.5,-497.5 4.5,-497.5"/>
+<text text-anchor="start" x="12.5" y="-663.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="74.5" y="-652.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
+<polyline fill="none" stroke="#000000" points="4.5,-645.5 144.5,-645.5 "/>
+<text text-anchor="middle" x="74.5" y="-633.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="4.5,-626.5 144.5,-626.5 "/>
+<text text-anchor="start" x="12.5" y="-614.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-603.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-592.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-581.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-570.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-559.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-548.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="12.5" y="-537.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="12.5" y="-526.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="12.5" y="-515.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="12.5" y="-504.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node4->Node3 -->
<g id="edge2" class="edge">
<title>Node4->Node3</title>
-<path fill="none" stroke="#404040" d="M70,-475.3167C70,-463.8765 70,-452.0062 70,-440.1402"/>
-<polygon fill="none" stroke="#404040" points="70.0001,-439.7944 66,-433.7944 70,-427.7944 74,-433.7943 70.0001,-439.7944"/>
-<text text-anchor="middle" x="89.5" y="-449" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
+<path fill="none" stroke="#404040" d="M74.5,-497.3167C74.5,-485.8765 74.5,-474.0062 74.5,-462.1402"/>
+<polygon fill="none" stroke="#404040" points="74.5001,-461.7944 70.5,-455.7944 74.5,-449.7944 78.5,-455.7943 74.5001,-461.7944"/>
+<text text-anchor="middle" x="94" y="-471" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg
index fe7c2ef2d..174005a5f 100644
--- a/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1meta__schedule_1_1Database__inherit__graph.svg
@@ -4,28 +4,30 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::meta_schedule::Database Pages: 1 -->
-<svg width="148pt" height="446pt"
- viewBox="0.00 0.00 148.00 446.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 442)">
+<svg width="157pt" height="468pt"
+ viewBox="0.00 0.00 157.00 468.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 464)">
<title>tvm::meta_schedule::Database</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-442 144,-442 144,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-464 153,-464 153,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-167.5 140,-167.5 140,-.5 0,-.5"/>
-<text text-anchor="start" x="8" y="-155.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
-<text text-anchor="middle" x="70" y="-144.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
-<polyline fill="none" stroke="#000000" points="0,-137.5 140,-137.5 "/>
-<text text-anchor="middle" x="70" y="-125.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-118.5 140,-118.5 "/>
-<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
-<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
-<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
-<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
-<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
-<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
-<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ScheduleFnDatabase()</text>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ JSONDatabase()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-189.5 149,-189.5 149,-.5 0,-.5"/>
+<text text-anchor="start" x="8" y="-177.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::meta_schedule</text>
+<text text-anchor="middle" x="74.5" y="-166.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">::Database</text>
+<polyline fill="none" stroke="#000000" points="0,-159.5 149,-159.5 "/>
+<text text-anchor="middle" x="74.5" y="-147.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-140.5 149,-140.5 "/>
+<text text-anchor="start" x="8" y="-128.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ EnterWithScope()</text>
+<text text-anchor="start" x="8" y="-117.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ExitWithScope()</text>
+<text text-anchor="start" x="8" y="-106.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_MUTABLE</text>
+<text text-anchor="start" x="8" y="-95.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_NOTNULLABLE_OBJECT</text>
+<text text-anchor="start" x="8" y="-84.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_REF_METHODS()</text>
+<text text-anchor="start" x="8" y="-73.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ MemoryDatabase()</text>
+<text text-anchor="start" x="8" y="-62.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ScheduleFnDatabase()</text>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ JSONDatabase()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ UnionDatabase()</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ OrderedUnionDatabase()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PyDatabase()</text>
<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Current()</text>
</g>
@@ -33,36 +35,36 @@
<g id="node2" class="node">
<title>Node1</title>
<g id="a_node2"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="3,-204.5 3,-437.5 137,-437.5 137,-204.5 3,-204.5"/>
-<text text-anchor="middle" x="70" y="-425.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="3,-418.5 137,-418.5 "/>
-<text text-anchor="start" x="11" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<text text-anchor="start" x="11" y="-395.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># data_</text>
-<polyline fill="none" stroke="#000000" points="3,-388.5 137,-388.5 "/>
-<text text-anchor="start" x="11" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="11" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="11" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="11" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="11" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="11" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="11" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="11" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="11" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="11" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="11" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="11" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="11" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="11" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="11" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="7.5,-226.5 7.5,-459.5 141.5,-459.5 141.5,-226.5 7.5,-226.5"/>
+<text text-anchor="middle" x="74.5" y="-447.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="7.5,-440.5 141.5,-440.5 "/>
+<text text-anchor="start" x="15.5" y="-428.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<text text-anchor="start" x="15.5" y="-417.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># data_</text>
+<polyline fill="none" stroke="#000000" points="7.5,-410.5 141.5,-410.5 "/>
+<text text-anchor="start" x="15.5" y="-398.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="15.5" y="-387.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="15.5" y="-376.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="15.5" y="-365.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="15.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="15.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="15.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="15.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="15.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="15.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="15.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="15.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="15.5" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="15.5" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="15.5" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="15.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node1->Node0 -->
<g id="edge1" class="edge">
<title>Node1->Node0</title>
-<path fill="none" stroke="#191970" d="M70,-194.0814C70,-185.1022 70,-176.1877 70,-167.5456"/>
-<polygon fill="none" stroke="#191970" points="66.5001,-194.2358 70,-204.2358 73.5001,-194.2358 66.5001,-194.2358"/>
+<path fill="none" stroke="#191970" d="M74.5,-216.1508C74.5,-207.1938 74.5,-198.2567 74.5,-189.5265"/>
+<polygon fill="none" stroke="#191970" points="71.0001,-216.2619 74.5,-226.2619 78.0001,-216.262 71.0001,-216.2619"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer-members.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer-members.html
index e30a2d76a..929c9d7d0 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer-members.html
@@ -87,10 +87,11 @@ $(function() {
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4744bf4a1b48f202d41b51dc5e08e6ee">operator<</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#affdf1b8cdb36e140de7b3ad7064e4617">operator==</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#ae31a5b9f40781d60a2901994ead700e8">same_as</a>(const ObjectRef &other) const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html#a8c69a0524ac9dd801f7f3735336a70ea">TVM_DEFINE_OBJECT_REF_METHODS</a>(DeclBuffer, Stmt, DeclBufferNode)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html">tvm::tir::DeclBuffer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1Stmt.html#aaca2f7bd4110028470b82825bcbb87ac">tvm::tir::Stmt::TVM_DEFINE_OBJECT_REF_METHODS</a>(Stmt, ObjectRef, StmtNode)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1Stmt.html">tvm::tir::Stmt</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a0ae0da21d247cd87ea94fe3777c4405e">use_count</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html#a7f85beba0bd46eeb7017b199290d838a">TVM_DEFINE_OBJECT_REF_COW_METHOD</a>(DeclBufferNode)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html">tvm::tir::DeclBuffer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html#a8c69a0524ac9dd801f7f3735336a70ea">TVM_DEFINE_OBJECT_REF_METHODS</a>(DeclBuffer, Stmt, DeclBufferNode)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html">tvm::tir::DeclBuffer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1tir_1_1Stmt.html#aaca2f7bd4110028470b82825bcbb87ac">tvm::tir::Stmt::TVM_DEFINE_OBJECT_REF_METHODS</a>(Stmt, ObjectRef, StmtNode)</td><td class="entry"><a class="el" href="classtvm_1_1tir_1_1Stmt.html">tvm::tir::Stmt</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a4e7cdb1574b93a59e784d70aa47b8da7">unique</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a0ae0da21d247cd87ea94fe3777c4405e">use_count</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
</table></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer.html b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer.html
index c8160738c..ddd79a9e3 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer.html
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer.html
@@ -77,13 +77,13 @@ $(function() {
<div class="dynheader">
Inheritance diagram for tvm::tir::DeclBuffer:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1tir_1_1DeclBuffer__inherit__graph.svg" width="216" height="618"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1tir_1_1DeclBuffer__inherit__graph.svg" width="216" height="647"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<div class="dynheader">
Collaboration diagram for tvm::tir::DeclBuffer:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg" width="216" height="907"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg" width="216" height="936"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<table class="memberdecls">
@@ -93,6 +93,8 @@ Public Member Functions</h2></td></tr>
<tr class="separator:a45dacd8c131761c6b8275f3da994e653"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a8c69a0524ac9dd801f7f3735336a70ea"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html#a8c69a0524ac9dd801f7f3735336a70ea">TVM_DEFINE_OBJECT_REF_METHODS</a> (<a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html">DeclBuffer</a>, <a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a>, <a class="el" href="classtvm_1_1tir_1_1DeclBufferNode.html">DeclBufferNode</a> [...]
<tr class="separator:a8c69a0524ac9dd801f7f3735336a70ea"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a7f85beba0bd46eeb7017b199290d838a"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html#a7f85beba0bd46eeb7017b199290d838a">TVM_DEFINE_OBJECT_REF_COW_METHOD</a> (<a class="el" href="classtvm_1_1tir_1_1DeclBufferNode.html">DeclBufferNode</a>)</td></tr>
+<tr class="separator:a7f85beba0bd46eeb7017b199290d838a"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="inherit_header pub_methods_classtvm_1_1tir_1_1Stmt"><td colspan="2" onclick="javascript:toggleInherit('pub_methods_classtvm_1_1tir_1_1Stmt')"><img src="closed.png" alt="-"/> Public Member Functions inherited from <a class="el" href="classtvm_1_1tir_1_1Stmt.html">tvm::tir::Stmt</a></td></tr>
<tr class="memitem:aaca2f7bd4110028470b82825bcbb87ac inherit pub_methods_classtvm_1_1tir_1_1Stmt"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1tir_1_1Stmt.html#aaca2f7bd4110028470b82825bcbb87ac">TVM_DEFINE_OBJECT_REF_METHODS</a> (<a class="el" href="classtvm_1_1tir_1_1Stmt.html">Stmt</a>, <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a>, <a class="el" href="classtvm_1_1tir_1_ [...]
<tr class="separator:aaca2f7bd4110028470b82825bcbb87ac inherit pub_methods_classtvm_1_1tir_1_1Stmt"><td class="memSeparator" colspan="2"> </td></tr>
@@ -197,6 +199,24 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
<h2 class="groupheader">Member Function Documentation</h2>
+<a id="a7f85beba0bd46eeb7017b199290d838a"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a7f85beba0bd46eeb7017b199290d838a">◆ </a></span>TVM_DEFINE_OBJECT_REF_COW_METHOD()</h2>
+
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">tvm::tir::DeclBuffer::TVM_DEFINE_OBJECT_REF_COW_METHOD </td>
+ <td>(</td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1tir_1_1DeclBufferNode.html">DeclBufferNode</a> </td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
<a id="a8c69a0524ac9dd801f7f3735336a70ea"></a>
<h2 class="memtitle"><span class="permalink"><a href="#a8c69a0524ac9dd801f7f3735336a70ea">◆ </a></span>TVM_DEFINE_OBJECT_REF_METHODS()</h2>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg
index d9855243b..18d846058 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__coll__graph.svg
@@ -4,107 +4,109 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::tir::DeclBuffer Pages: 1 -->
-<svg width="162pt" height="680pt"
- viewBox="0.00 0.00 162.00 680.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 676)">
+<svg width="162pt" height="702pt"
+ viewBox="0.00 0.00 162.00 702.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 698)">
<title>tvm::tir::DeclBuffer</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-676 158,-676 158,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-698 158,-698 158,4 -4,4"/>
<!-- Node3 -->
<g id="node1" class="node">
<title>Node3</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-79.5 154,-79.5 154,-.5 0,-.5"/>
-<text text-anchor="middle" x="77" y="-67.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::DeclBuffer</text>
-<polyline fill="none" stroke="#000000" points="0,-60.5 154,-60.5 "/>
-<text text-anchor="middle" x="77" y="-48.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-41.5 154,-41.5 "/>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DeclBuffer()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-101.5 154,-101.5 154,-.5 0,-.5"/>
+<text text-anchor="middle" x="77" y="-89.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::DeclBuffer</text>
+<polyline fill="none" stroke="#000000" points="0,-82.5 154,-82.5 "/>
+<text text-anchor="middle" x="77" y="-70.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-63.5 154,-63.5 "/>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DeclBuffer()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_COW_METHOD()</text>
</g>
<!-- Node4 -->
<g id="node2" class="node">
<title>Node4</title>
<g id="a_node2"><a xlink:href="classtvm_1_1tir_1_1Stmt.html" target="_top" xlink:title="Container of all statements. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-117.5 0,-185.5 154,-185.5 154,-117.5 0,-117.5"/>
-<text text-anchor="middle" x="77" y="-173.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::Stmt</text>
-<polyline fill="none" stroke="#000000" points="0,-166.5 154,-166.5 "/>
-<text text-anchor="middle" x="77" y="-154.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-147.5 154,-147.5 "/>
-<text text-anchor="start" x="8" y="-135.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="8" y="-124.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-139.5 0,-207.5 154,-207.5 154,-139.5 0,-139.5"/>
+<text text-anchor="middle" x="77" y="-195.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::Stmt</text>
+<polyline fill="none" stroke="#000000" points="0,-188.5 154,-188.5 "/>
+<text text-anchor="middle" x="77" y="-176.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-169.5 154,-169.5 "/>
+<text text-anchor="start" x="8" y="-157.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="8" y="-146.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
</a>
</g>
</g>
<!-- Node4->Node3 -->
<g id="edge1" class="edge">
<title>Node4->Node3</title>
-<path fill="none" stroke="#191970" d="M77,-107.3732C77,-98.2436 77,-88.6788 77,-79.718"/>
-<polygon fill="none" stroke="#191970" points="73.5001,-107.4404 77,-117.4405 80.5001,-107.4405 73.5001,-107.4404"/>
+<path fill="none" stroke="#191970" d="M77,-129.2437C77,-120.3671 77,-110.9733 77,-101.8923"/>
+<polygon fill="none" stroke="#191970" points="73.5001,-129.3769 77,-139.3769 80.5001,-129.377 73.5001,-129.3769"/>
</g>
<!-- Node5 -->
<g id="node3" class="node">
<title>Node5</title>
<g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="10,-223.5 10,-445.5 144,-445.5 144,-223.5 10,-223.5"/>
-<text text-anchor="middle" x="77" y="-433.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="10,-426.5 144,-426.5 "/>
-<text text-anchor="start" x="18" y="-414.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="10,-407.5 144,-407.5 "/>
-<text text-anchor="start" x="18" y="-395.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="18" y="-384.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="18" y="-373.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="18" y="-362.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="18" y="-351.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="18" y="-340.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="18" y="-329.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="18" y="-318.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="18" y="-307.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="18" y="-296.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="18" y="-285.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="18" y="-274.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="18" y="-263.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="18" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="18" y="-241.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="18" y="-230.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="10,-245.5 10,-467.5 144,-467.5 144,-245.5 10,-245.5"/>
+<text text-anchor="middle" x="77" y="-455.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="10,-448.5 144,-448.5 "/>
+<text text-anchor="start" x="18" y="-436.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="10,-429.5 144,-429.5 "/>
+<text text-anchor="start" x="18" y="-417.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="18" y="-406.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="18" y="-395.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="18" y="-384.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="18" y="-373.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="18" y="-362.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="18" y="-351.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="18" y="-340.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="18" y="-329.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="18" y="-318.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="18" y="-307.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="18" y="-296.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="18" y="-285.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="18" y="-274.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="18" y="-263.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="18" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node5->Node4 -->
<g id="edge2" class="edge">
<title>Node5->Node4</title>
-<path fill="none" stroke="#191970" d="M77,-213.2198C77,-203.2931 77,-193.8914 77,-185.5572"/>
-<polygon fill="none" stroke="#191970" points="73.5001,-213.3012 77,-223.3012 80.5001,-213.3012 73.5001,-213.3012"/>
+<path fill="none" stroke="#191970" d="M77,-235.2198C77,-225.2931 77,-215.8914 77,-207.5572"/>
+<polygon fill="none" stroke="#191970" points="73.5001,-235.3012 77,-245.3012 80.5001,-235.3012 73.5001,-235.3012"/>
</g>
<!-- Node6 -->
<g id="node4" class="node">
<title>Node6</title>
<g id="a_node4"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\< tvm::runtime::Object \>\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator-\>()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="7,-493.5 7,-671.5 147,-671.5 147,-493.5 7,-493.5"/>
-<text text-anchor="start" x="15" y="-659.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="77" y="-648.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
-<polyline fill="none" stroke="#000000" points="7,-641.5 147,-641.5 "/>
-<text text-anchor="middle" x="77" y="-629.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="7,-622.5 147,-622.5 "/>
+<polygon fill="#ffffff" stroke="#000000" points="7,-515.5 7,-693.5 147,-693.5 147,-515.5 7,-515.5"/>
+<text text-anchor="start" x="15" y="-681.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="77" y="-670.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
+<polyline fill="none" stroke="#000000" points="7,-663.5 147,-663.5 "/>
+<text text-anchor="middle" x="77" y="-651.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="7,-644.5 147,-644.5 "/>
+<text text-anchor="start" x="15" y="-632.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="15" y="-621.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="15" y="-610.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="15" y="-599.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="15" y="-588.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
<text text-anchor="start" x="15" y="-577.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="15" y="-566.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="15" y="-555.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="15" y="-544.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="15" y="-533.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="15" y="-522.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="15" y="-511.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="15" y="-500.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<text text-anchor="start" x="15" y="-566.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="15" y="-555.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="15" y="-544.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="15" y="-533.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="15" y="-522.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node6->Node5 -->
<g id="edge3" class="edge">
<title>Node6->Node5</title>
-<path fill="none" stroke="#404040" d="M77,-493.3167C77,-481.8765 77,-470.0062 77,-458.1402"/>
-<polygon fill="none" stroke="#404040" points="77.0001,-457.7944 73,-451.7944 77,-445.7944 81,-451.7943 77.0001,-457.7944"/>
-<text text-anchor="middle" x="96.5" y="-467" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
+<path fill="none" stroke="#404040" d="M77,-515.3167C77,-503.8765 77,-492.0062 77,-480.1402"/>
+<polygon fill="none" stroke="#404040" points="77.0001,-479.7944 73,-473.7944 77,-467.7944 81,-473.7943 77.0001,-479.7944"/>
+<text text-anchor="middle" x="96.5" y="-489" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__inherit__graph.svg
index 5d7f3bf1d..4eae01fb4 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1DeclBuffer__inherit__graph.svg
@@ -4,77 +4,79 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::tir::DeclBuffer Pages: 1 -->
-<svg width="162pt" height="463pt"
- viewBox="0.00 0.00 162.00 463.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 459)">
+<svg width="162pt" height="485pt"
+ viewBox="0.00 0.00 162.00 485.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 481)">
<title>tvm::tir::DeclBuffer</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-459 158,-459 158,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-481 158,-481 158,4 -4,4"/>
<!-- Node0 -->
<g id="node1" class="node">
<title>Node0</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-79.5 154,-79.5 154,-.5 0,-.5"/>
-<text text-anchor="middle" x="77" y="-67.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::DeclBuffer</text>
-<polyline fill="none" stroke="#000000" points="0,-60.5 154,-60.5 "/>
-<text text-anchor="middle" x="77" y="-48.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-41.5 154,-41.5 "/>
-<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DeclBuffer()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="0,-.5 0,-101.5 154,-101.5 154,-.5 0,-.5"/>
+<text text-anchor="middle" x="77" y="-89.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::DeclBuffer</text>
+<polyline fill="none" stroke="#000000" points="0,-82.5 154,-82.5 "/>
+<text text-anchor="middle" x="77" y="-70.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-63.5 154,-63.5 "/>
+<text text-anchor="start" x="8" y="-51.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DeclBuffer()</text>
+<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_COW_METHOD()</text>
</g>
<!-- Node1 -->
<g id="node2" class="node">
<title>Node1</title>
<g id="a_node2"><a xlink:href="classtvm_1_1tir_1_1Stmt.html" target="_top" xlink:title="Container of all statements. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-116.5 0,-184.5 154,-184.5 154,-116.5 0,-116.5"/>
-<text text-anchor="middle" x="77" y="-172.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::Stmt</text>
-<polyline fill="none" stroke="#000000" points="0,-165.5 154,-165.5 "/>
-<text text-anchor="middle" x="77" y="-153.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="0,-146.5 154,-146.5 "/>
-<text text-anchor="start" x="8" y="-134.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="8" y="-123.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-138.5 0,-206.5 154,-206.5 154,-138.5 0,-138.5"/>
+<text text-anchor="middle" x="77" y="-194.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::Stmt</text>
+<polyline fill="none" stroke="#000000" points="0,-187.5 154,-187.5 "/>
+<text text-anchor="middle" x="77" y="-175.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="0,-168.5 154,-168.5 "/>
+<text text-anchor="start" x="8" y="-156.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="8" y="-145.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
</a>
</g>
</g>
<!-- Node1->Node0 -->
<g id="edge1" class="edge">
<title>Node1->Node0</title>
-<path fill="none" stroke="#191970" d="M77,-106.3044C77,-97.4634 77,-88.2287 77,-79.5566"/>
-<polygon fill="none" stroke="#191970" points="73.5001,-106.4447 77,-116.4447 80.5001,-106.4447 73.5001,-106.4447"/>
+<path fill="none" stroke="#191970" d="M77,-128.1349C77,-119.5408 77,-110.474 77,-101.6952"/>
+<polygon fill="none" stroke="#191970" points="73.5001,-128.3321 77,-138.3321 80.5001,-128.3322 73.5001,-128.3321"/>
</g>
<!-- Node2 -->
<g id="node3" class="node">
<title>Node2</title>
<g id="a_node3"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="10,-221.5 10,-454.5 144,-454.5 144,-221.5 10,-221.5"/>
-<text text-anchor="middle" x="77" y="-442.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="10,-435.5 144,-435.5 "/>
-<text text-anchor="start" x="18" y="-423.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<text text-anchor="start" x="18" y="-412.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># data_</text>
-<polyline fill="none" stroke="#000000" points="10,-405.5 144,-405.5 "/>
-<text text-anchor="start" x="18" y="-393.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="18" y="-382.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="18" y="-371.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="18" y="-360.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="18" y="-349.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="18" y="-338.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="18" y="-327.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="18" y="-316.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="18" y="-305.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="18" y="-294.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="18" y="-283.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="18" y="-272.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="18" y="-261.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="18" y="-250.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="18" y="-239.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="18" y="-228.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="10,-243.5 10,-476.5 144,-476.5 144,-243.5 10,-243.5"/>
+<text text-anchor="middle" x="77" y="-464.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="10,-457.5 144,-457.5 "/>
+<text text-anchor="start" x="18" y="-445.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<text text-anchor="start" x="18" y="-434.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># data_</text>
+<polyline fill="none" stroke="#000000" points="10,-427.5 144,-427.5 "/>
+<text text-anchor="start" x="18" y="-415.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="18" y="-404.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="18" y="-393.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="18" y="-382.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="18" y="-371.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="18" y="-360.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="18" y="-349.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="18" y="-338.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="18" y="-327.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="18" y="-316.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="18" y="-305.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="18" y="-294.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="18" y="-283.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="18" y="-272.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="18" y="-261.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="18" y="-250.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node2->Node1 -->
<g id="edge2" class="edge">
<title>Node2->Node1</title>
-<path fill="none" stroke="#191970" d="M77,-211.2822C77,-201.749 77,-192.737 77,-184.7166"/>
-<polygon fill="none" stroke="#191970" points="73.5001,-211.3857 77,-221.3857 80.5001,-211.3857 73.5001,-211.3857"/>
+<path fill="none" stroke="#191970" d="M77,-233.2822C77,-223.749 77,-214.737 77,-206.7166"/>
+<polygon fill="none" stroke="#191970" points="73.5001,-233.3857 77,-243.3857 80.5001,-233.3857 73.5001,-233.3857"/>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/classtvm_1_1tir_1_1Stmt__inherit__graph.svg b/docs/reference/api/doxygen/classtvm_1_1tir_1_1Stmt__inherit__graph.svg
index d23a65a65..63071a497 100644
--- a/docs/reference/api/doxygen/classtvm_1_1tir_1_1Stmt__inherit__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1tir_1_1Stmt__inherit__graph.svg
@@ -202,21 +202,23 @@
<g id="node11" class="node">
<title>Node10</title>
<g id="a_node11"><a xlink:href="classtvm_1_1tir_1_1DeclBuffer.html" target="_top" xlink:title="Managed reference to DeclBufferNode. ">
-<polygon fill="#ffffff" stroke="#000000" points="1388,-17 1388,-96 1542,-96 1542,-17 1388,-17"/>
-<text text-anchor="middle" x="1465" y="-84" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::DeclBuffer</text>
-<polyline fill="none" stroke="#000000" points="1388,-77 1542,-77 "/>
-<text text-anchor="middle" x="1465" y="-65" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="1388,-58 1542,-58 "/>
-<text text-anchor="start" x="1396" y="-46" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DeclBuffer()</text>
-<text text-anchor="start" x="1396" y="-35" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="1396" y="-24" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<polygon fill="#ffffff" stroke="#000000" points="1388,-6 1388,-107 1542,-107 1542,-6 1388,-6"/>
+<text text-anchor="middle" x="1465" y="-95" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::tir::DeclBuffer</text>
+<polyline fill="none" stroke="#000000" points="1388,-88 1542,-88 "/>
+<text text-anchor="middle" x="1465" y="-76" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="1388,-69 1542,-69 "/>
+<text text-anchor="start" x="1396" y="-57" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DeclBuffer()</text>
+<text text-anchor="start" x="1396" y="-46" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="1396" y="-35" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<text text-anchor="start" x="1396" y="-24" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="1396" y="-13" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_COW_METHOD()</text>
</a>
</g>
</g>
<!-- Node0->Node10 -->
<g id="edge10" class="edge">
<title>Node0->Node10</title>
-<path fill="none" stroke="#191970" d="M1582.6222,-143.3489C1562.16,-128.2402 1538.9229,-111.0826 1518.5378,-96.0309"/>
+<path fill="none" stroke="#191970" d="M1582.4565,-143.2266C1566.9231,-131.7572 1549.8017,-119.1152 1533.5485,-107.1143"/>
<polygon fill="none" stroke="#191970" points="1580.7835,-146.342 1590.9072,-149.4663 1584.9415,-140.7107 1580.7835,-146.342"/>
</g>
<!-- Node11 -->
diff --git a/docs/reference/api/doxygen/compilation__config_8h_source.html b/docs/reference/api/doxygen/compilation__config_8h_source.html
index e78b8b073..2be5fee56 100644
--- a/docs/reference/api/doxygen/compilation__config_8h_source.html
+++ b/docs/reference/api/doxygen/compilation__config_8h_source.html
@@ -68,7 +68,7 @@ $(function() {
<div class="contents">
<a href="compilation__config_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * [...]
<div class="ttc" id="classtvm_1_1CompilationConfig_html"><div class="ttname"><a href="classtvm_1_1CompilationConfig.html">tvm::CompilationConfig</a></div><div class="ttdoc">Managed reference class to CompilationConfig. </div><div class="ttdef"><b>Definition:</b> compilation_config.h:191</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a7e4e7cd47471a9089022214d63d24206"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a7e4e7cd47471a9089022214d63d24206">tvm::tir::attr::device_type</a></div><div class="ttdeci">constexpr const char * device_type</div><div class="ttdoc">The device type. </div><div class="ttdef"><b>Definition:</b> stmt.h:1391</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a7e4e7cd47471a9089022214d63d24206"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a7e4e7cd47471a9089022214d63d24206">tvm::tir::attr::device_type</a></div><div class="ttdeci">constexpr const char * device_type</div><div class="ttdoc">The device type. </div><div class="ttdef"><b>Definition:</b> stmt.h:1392</div></div>
<div class="ttc" id="virtual__device_8h_html"><div class="ttname"><a href="virtual__device_8h.html">virtual_device.h</a></div><div class="ttdoc">A compile time representation for where data is to be stored at runtime, and how to compile code to c...</div></div>
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="classtvm_1_1VirtualDevice_html_a8238a76dcecef304fa173ceaf706c7b1"><div class="ttname"><a href="classtvm_1_1VirtualDevice.html#a8238a76dcecef304fa173ceaf706c7b1">tvm::VirtualDevice::FullyUnconstrained</a></div><div class="ttdeci">static VirtualDevice FullyUnconstrained()</div><div class="ttdoc">Returns the unique fully unconstrained VirtualDevice. </div></div>
diff --git a/docs/reference/api/doxygen/database_8h_source.html b/docs/reference/api/doxygen/database_8h_source.html
index 1fa809d07..8bbf0704e 100644
--- a/docs/reference/api/doxygen/database_8h_source.html
+++ b/docs/reference/api/doxygen/database_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">database.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="database_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more co [...]
+<a href="database_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more co [...]
<div class="ttc" id="classtvm_1_1meta__schedule_1_1WorkloadNode_html_a93d2f3debadefcc713bbc045127ca8f7"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1WorkloadNode.html#a93d2f3debadefcc713bbc045127ca8f7">tvm::meta_schedule::WorkloadNode::TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_FINAL_OBJECT_INFO(WorkloadNode, runtime::Object)</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1PyDatabaseNode_html_a7d7d50ae9b6c43e064b38db91bc8123d"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1PyDatabaseNode.html#a7d7d50ae9b6c43e064b38db91bc8123d">tvm::meta_schedule::PyDatabaseNode::f_commit_tuning_record</a></div><div class="ttdeci">FCommitTuningRecord f_commit_tuning_record</div><div class="ttdoc">The packed function to the CommitTuningRecord function. </div><div class="ttdef"><b>Definition:</b> database.h:281</d [...]
<div class="ttc" id="trace_8h_html"><div class="ttname"><a href="trace_8h.html">trace.h</a></div></div>
diff --git a/docs/reference/api/doxygen/detail_2extern_8h_source.html b/docs/reference/api/doxygen/detail_2extern_8h_source.html
index 04ea38073..d60f51473 100644
--- a/docs/reference/api/doxygen/detail_2extern_8h_source.html
+++ b/docs/reference/api/doxygen/detail_2extern_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="operation_8h_html"><div class="ttname"><a href="operation_8h.html">operation.h</a></div><div class="ttdoc">Operation node can generate one or multiple Tensors. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Map_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Map.html">tvm::runtime::Map</a></div><div class="ttdoc">Map container of NodeRef->NodeRef in DSL graph. Map implements copy on write semantics, which means map is mutable but copy will happen when array is referenced in more than two places. </div><div class="ttdef"><b>Definition:</b> map.h:1268</div></div>
<div class="ttc" id="builtin_8h_html"><div class="ttname"><a href="builtin_8h.html">builtin.h</a></div><div class="ttdoc">TIR builtin intrinsics. </div></div>
-<div class="ttc" id="classtvm_1_1tir_1_1Evaluate_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Evaluate.html">tvm::tir::Evaluate</a></div><div class="ttdoc">Managed reference to EvaluateNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:892</div></div>
+<div class="ttc" id="classtvm_1_1tir_1_1Evaluate_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Evaluate.html">tvm::tir::Evaluate</a></div><div class="ttdoc">Managed reference to EvaluateNode. </div><div class="ttdef"><b>Definition:</b> stmt.h:893</div></div>
<div class="ttc" id="namespacetvm_html_a41918af1a1dc386388639a9d3ad06c5d"><div class="ttname"><a href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">tvm::DataType</a></div><div class="ttdeci">runtime::DataType DataType</div><div class="ttdef"><b>Definition:</b> data_type.h:389</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html_ab45f13dd70d982d9f977c79b6f7fac98"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html#ab45f13dd70d982d9f977c79b6f7fac98">tvm::runtime::DataType::Int</a></div><div class="ttdeci">static DataType Int(int bits, int lanes=1)</div><div class="ttdoc">Construct an int type. </div><div class="ttdef"><b>Definition:</b> data_type.h:154</div></div>
</div><!-- fragment --></div><!-- contents -->
diff --git a/docs/reference/api/doxygen/device__api_8h_source.html b/docs/reference/api/doxygen/device__api_8h_source.html
index cbe4f3a3e..0fe17d857 100644
--- a/docs/reference/api/doxygen/device__api_8h_source.html
+++ b/docs/reference/api/doxygen/device__api_8h_source.html
@@ -68,7 +68,7 @@ $(function() {
<div class="contents">
<a href="device__api_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more [...]
<div class="ttc" id="classtvm_1_1runtime_1_1TVMRetValue_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMRetValue.html">tvm::runtime::TVMRetValue</a></div><div class="ttdoc">Return Value container, Unlike TVMArgValue, which only holds reference and do not delete the underlyi...</div><div class="ttdef"><b>Definition:</b> packed_func.h:799</div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a7e4e7cd47471a9089022214d63d24206"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a7e4e7cd47471a9089022214d63d24206">tvm::tir::attr::device_type</a></div><div class="ttdeci">constexpr const char * device_type</div><div class="ttdoc">The device type. </div><div class="ttdef"><b>Definition:</b> stmt.h:1391</div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1attr_html_a7e4e7cd47471a9089022214d63d24206"><div class="ttname"><a href="namespacetvm_1_1tir_1_1attr.html#a7e4e7cd47471a9089022214d63d24206">tvm::tir::attr::device_type</a></div><div class="ttdeci">constexpr const char * device_type</div><div class="ttdoc">The device type. </div><div class="ttdef"><b>Definition:</b> stmt.h:1392</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619a69fe0643750b0c49e8b8aefb1cada337"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619a69fe0643750b0c49e8b8aefb1cada337">tvm::runtime::kApiVersion</a></div><div class="ttdef"><b>Definition:</b> device_api.h:50</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a551bab1e24e2e794f8ccd4446b63a7af"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a551bab1e24e2e794f8ccd4446b63a7af">tvm::runtime::kDefaultWorkspaceAlignment</a></div><div class="ttdeci">constexpr int kDefaultWorkspaceAlignment</div><div class="ttdoc">Number of bytes each allocation must align to by default in the workspace buffer to service intermedi...</div><div class="ttdef"><b>Definition:</b> device_api.h:65</div></div>
<div class="ttc" id="c__runtime__api_8h_html_a57cbccb14c35a0e62dbc1b911188fcefacdc33f5efa9ddabe89e886c28d1ff65b"><div class="ttname"><a href="c__runtime__api_8h.html#a57cbccb14c35a0e62dbc1b911188fcefacdc33f5efa9ddabe89e886c28d1ff65b">kDLSDAccel</a></div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:86</div></div>
diff --git a/docs/reference/api/doxygen/functions_func_o.html b/docs/reference/api/doxygen/functions_func_o.html
index e96b838f7..68135ffbc 100644
--- a/docs/reference/api/doxygen/functions_func_o.html
+++ b/docs/reference/api/doxygen/functions_func_o.html
@@ -323,7 +323,7 @@ $(function() {
, <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ada44b624c1397c943ad9a0427378b048">tvm::tir::SizeVar</a>
, <a class="el" href="classtvm_1_1tir_1_1Var.html#a6a5db358f4fd7a9005a2d7a5f0fbe501">tvm::tir::Var</a>
, <a class="el" href="classtvm_1_1TracedMapIterator.html#a47366afaaedf33630bb24f6c2fbb8a79">tvm::TracedMapIterator< K, V ></a>
-, <a class="el" href="classtvm_1_1transform_1_1PassContext.html#a2d1a6fffe70703812245b8d834da9a44">tvm::transform::PassContext</a>
+, <a class="el" href="classtvm_1_1transform_1_1PassContext.html#ab10baf6f7bcbd6e0e4b295399bc9f3a9">tvm::transform::PassContext</a>
, <a class="el" href="classtvm_1_1transform_1_1Sequential.html#a326b2bc7ce7710e22a91265b3aff37a0">tvm::transform::Sequential</a>
, <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#ab0177fd981b51149651e8912e6bf1b68">tvm::TypedEnvFunc< R(Args...)></a>
, <a class="el" href="classtvm_1_1TypeReporter.html#a64f4543a37a87db2fc57039a4ee6d3af">tvm::TypeReporter</a>
@@ -345,12 +345,12 @@ $(function() {
, <a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html#a98237b6a6448ba4ed10f64c3016eb4e2">tvm::relay::PatternWildcard</a>
, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a8f52fa8c97344586060ca735a3b91b39">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#a6b398835e5160e792634c8ee0783f284">tvm::runtime::Map< K, V, typename, typename ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">tvm::runtime::Object</a>
-, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#a4ea3532cb25b896b47b609c7db788bf8">tvm::runtime::ObjectPtr< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">tvm::runtime::Object</a>
+, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#afda3c65f41e83e1c87145a216f8c846d">tvm::runtime::ObjectPtr< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#af840ea1549dbe89d1680025c803e02e1">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1String.html#a3b3c8614af05adc454f47132e04552ed">tvm::runtime::String</a>
, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#a4993d4b338c28096b56ed3d0d9ae5170">tvm::runtime::TVMRetValue</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#aa590b3e712e06867805b41aaf17019ed">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8dd1fbae84cb9597c52977b0e8db64dc">tvm::runtime::TypedPackedFunc< R(Args...)></a>
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a69c12a9470f67ea26e53172f5c9220a1">tvm::runtime::vm::Instruction</a>
, <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#aab332907b9f98876f441f6403b801187">tvm::TypedEnvFunc< R(Args...)></a>
</li>
@@ -361,9 +361,9 @@ $(function() {
, <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#ade3c126684dcdc6ed432f3bb7eb62099">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a264c17028af85fe4619852f804e9464a">tvm::runtime::MapNode::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayIterator.html#a6941bd0a5aa77acb1069e099e08455ed">tvm::runtime::metadata::ArrayIterator< C, Ref ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#ab849841f9277ad9015515ed591bf79d3">tvm::runtime::ObjectPtr< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#aeb6535554bf4a31d0e0bf80d5f23db29">tvm::runtime::ObjectPtr< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#affdf1b8cdb36e140de7b3ad7064e4617">tvm::runtime::ObjectRef</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a2e5b8e5065518ef40c70d5575edf8806">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#ae162e2c75ca786277c01a0f91b157fee">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1PackedFunc.html#a5c4ed23ffcb6a1874bd6eceb87b40b25">tvm::runtime::PackedFunc</a>
, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#ae71116873ea643de9f8ec1836cc116db">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a0e4a4d01d86eca79c5d9e1e90322c5cb">tvm::runtime::TypedPackedFunc< R(Args...)></a>
@@ -406,11 +406,14 @@ $(function() {
</li>
<li>Optional()
: <a class="el" href="classtvm_1_1relay_1_1DFPattern.html#aa573fa65bf9c4f0ba090225105233136">tvm::relay::DFPattern</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a4474559794818ad1257b70e681929938">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a37dde5a68fe4e1f13494a66f79da419b">tvm::runtime::Optional< T ></a>
</li>
<li>Or()
: <a class="el" href="classtvm_1_1tir_1_1Or.html#ab0b68884ed84d03d3af7c95da2fcf81e">tvm::tir::Or</a>
</li>
+<li>OrderedUnionDatabase()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#ae4f6e0e951be446d2ab836eb8a9bcc83">tvm::meta_schedule::Database</a>
+</li>
<li>output()
: <a class="el" href="classtvm_1_1te_1_1Operation.html#a00b67945c799a2022d3164ab63dd3b82">tvm::te::Operation</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_func_s.html b/docs/reference/api/doxygen/functions_func_s.html
index 1e2a181f1..e42f50b21 100644
--- a/docs/reference/api/doxygen/functions_func_s.html
+++ b/docs/reference/api/doxygen/functions_func_s.html
@@ -620,7 +620,7 @@ $(function() {
, <a class="el" href="classtvm_1_1TracedArray.html#a52b30a89b5c68811d0789f9f32b12627">tvm::TracedArray< T ></a>
</li>
<li>SizeVar()
-: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#a0f8cb8a92feb96343939d223db90f7cd">tvm::tir::SizeVar</a>
+: <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ac470249315d9e395ad581d35dd5dcb05">tvm::tir::SizeVar</a>
</li>
<li>Slice()
: <a class="el" href="classtvm_1_1te_1_1Tensor_1_1Slice.html#ab314819e8bcca6421e9a4f33e48578c3">tvm::te::Tensor::Slice</a>
@@ -731,7 +731,7 @@ $(function() {
: <a class="el" href="classtvm_1_1tir_1_1ScheduleNode.html#a93d1d23f24d903db844f75f51fe09a36">tvm::tir::ScheduleNode</a>
</li>
<li>StorageAlignStep()
-: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#a99dbb8c55d9e7d78268b6d43fd348bc7">tvm::auto_scheduler::StorageAlignStep</a>
+: <a class="el" href="classtvm_1_1auto__scheduler_1_1StorageAlignStep.html#af50b7c2f020f8e0a80f5bcc8e559b394">tvm::auto_scheduler::StorageAlignStep</a>
</li>
<li>Store()
: <a class="el" href="classtvm_1_1tir_1_1Store.html#a2c4278b8bcdae57ada2022ecc7c290c3">tvm::tir::Store</a>
@@ -746,7 +746,7 @@ $(function() {
: <a class="el" href="classtvm_1_1runtime_1_1DeviceAPI.html#ac29b9295c432a87658392872c644864f">tvm::runtime::DeviceAPI</a>
</li>
<li>String()
-: <a class="el" href="classtvm_1_1runtime_1_1String.html#acf549b3c43142639879e0fc31ea5cd77">tvm::runtime::String</a>
+: <a class="el" href="classtvm_1_1runtime_1_1String.html#a02fca36e3ff55cc1e83635b02a11fca3">tvm::runtime::String</a>
</li>
<li>StringImm()
: <a class="el" href="classtvm_1_1tir_1_1StringImm.html#a0f2830290e055f677c5d5dea98aab726">tvm::tir::StringImm</a>
diff --git a/docs/reference/api/doxygen/functions_func_t.html b/docs/reference/api/doxygen/functions_func_t.html
index 1b7e969ff..69b15143e 100644
--- a/docs/reference/api/doxygen/functions_func_t.html
+++ b/docs/reference/api/doxygen/functions_func_t.html
@@ -920,6 +920,7 @@ $(function() {
, <a class="el" href="classtvm_1_1tir_1_1BufferRealize.html#ab115e581dae14362ca1efd9068be014b">tvm::tir::BufferRealize</a>
, <a class="el" href="classtvm_1_1tir_1_1BufferRegion.html#a8decdd1e677ab8000e6cbcbe4eca162a">tvm::tir::BufferRegion</a>
, <a class="el" href="classtvm_1_1tir_1_1BufferStore.html#ae2747c11c1d1d4a89f1ef3aff6fe3955">tvm::tir::BufferStore</a>
+, <a class="el" href="classtvm_1_1tir_1_1DeclBuffer.html#a7f85beba0bd46eeb7017b199290d838a">tvm::tir::DeclBuffer</a>
, <a class="el" href="classtvm_1_1tir_1_1For.html#a42939929f57f4990e03ebd3f6d644051">tvm::tir::For</a>
, <a class="el" href="classtvm_1_1tir_1_1IterVar.html#a274f036355aace7525f37baf65452f84">tvm::tir::IterVar</a>
, <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html#a1670eb2c0453ed14f7caf004df9a42d8">tvm::tir::PrimFunc</a>
@@ -1144,7 +1145,7 @@ $(function() {
: <a class="el" href="classtvm_1_1runtime_1_1TVMPODValue__.html#a2f46b59a6c1d5eb4575d7f583b5f1a0c">tvm::runtime::TVMPODValue_</a>
</li>
<li>TVMRetValue()
-: <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#a77455a8fe7d27b90a01a64f1cd28e9ec">tvm::runtime::TVMRetValue</a>
+: <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#ac4a3850c0989e7c2d5cd8e0f096d0997">tvm::runtime::TVMRetValue</a>
</li>
<li>type()
: <a class="el" href="classtvm_1_1runtime_1_1vm_1_1Allocator.html#a7cfb6d4ea480436801276fe2e7660eb2">tvm::runtime::vm::Allocator</a>
@@ -1170,10 +1171,10 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeData.html#a0a98fd1095812379d2bd1337db1511c1">tvm::TypeData</a>
</li>
<li>TypedEnvFunc()
-: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a41a6b9014d0feeb628ca7edfd0d26f0b">tvm::TypedEnvFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#a0d72a6fa7263821c14bcd37837998ed9">tvm::TypedEnvFunc< R(Args...)></a>
</li>
<li>TypedPackedFunc()
-: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8941c80982a1b2a289440f3c79bb0ac8">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+: <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#af45a2ceff92e6f6c394ea766a45027a0">tvm::runtime::TypedPackedFunc< R(Args...)></a>
</li>
<li>TypeIndex2Key()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#a817ba6c23b7ee1821c48a75edf255a30">tvm::runtime::Object</a>
@@ -1196,7 +1197,7 @@ $(function() {
: <a class="el" href="classtvm_1_1TypeRelation.html#ac26b1897eab8197ed26606ab81b7403b">tvm::TypeRelation</a>
</li>
<li>TypeReporter()
-: <a class="el" href="classtvm_1_1TypeReporter.html#a8e7e05a07f9f7ad9bea91f27afac9051">tvm::TypeReporter</a>
+: <a class="el" href="classtvm_1_1TypeReporter.html#aa3dc38a3c84d324d0b3a9f358460a091">tvm::TypeReporter</a>
</li>
<li>TypeVar()
: <a class="el" href="classtvm_1_1TypeVar.html#adf5ef8e89d162735519b5d125c89e3e3">tvm::TypeVar</a>
diff --git a/docs/reference/api/doxygen/functions_func_u.html b/docs/reference/api/doxygen/functions_func_u.html
index 88e21c212..611cae9ff 100644
--- a/docs/reference/api/doxygen/functions_func_u.html
+++ b/docs/reference/api/doxygen/functions_func_u.html
@@ -73,6 +73,9 @@ $(function() {
<li>Unframer()
: <a class="el" href="classtvm_1_1runtime_1_1micro__rpc_1_1Unframer.html#a58d68e70d1819a706669c9934dd07639">tvm::runtime::micro_rpc::Unframer</a>
</li>
+<li>UnionDatabase()
+: <a class="el" href="classtvm_1_1meta__schedule_1_1Database.html#affcd4ddc4911a83f281de558366a6d63">tvm::meta_schedule::Database</a>
+</li>
<li>unique()
: <a class="el" href="classtvm_1_1runtime_1_1Object.html#afd548730a6139d19fe24473ad66026d7">tvm::runtime::Object</a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#af95c6c6fcd89da0f62b93f1167b72314">tvm::runtime::ObjectPtr< T ></a>
@@ -103,7 +106,7 @@ $(function() {
, <a class="el" href="classtvm_1_1auto__scheduler_1_1CostModelNode.html#ae35b2b678760b8da57a43d3ae9c24da5">tvm::auto_scheduler::CostModelNode</a>
, <a class="el" href="classtvm_1_1auto__scheduler_1_1PythonBasedModelNode.html#a2d7849df6c7dbe93bf363c1d9f860a26">tvm::auto_scheduler::PythonBasedModelNode</a>
, <a class="el" href="classtvm_1_1auto__scheduler_1_1RandomModelNode.html#a7febac6c05d8e2d407f466467769ee32">tvm::auto_scheduler::RandomModelNode</a>
-, <a class="el" href="classtvm_1_1IRModuleNode.html#a94a93385e64ce844299729af6a573015">tvm::IRModuleNode</a>
+, <a class="el" href="classtvm_1_1IRModuleNode.html#abdd8936c6fca33ef9b7c086f8fd58f84">tvm::IRModuleNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1CostModelNode.html#a1bba32eba84db583fe90d1a5bce085f1">tvm::meta_schedule::CostModelNode</a>
, <a class="el" href="classtvm_1_1meta__schedule_1_1PyCostModelNode.html#a970b00b0eb1bf6b88eea2711b58c4d1d">tvm::meta_schedule::PyCostModelNode</a>
</li>
diff --git a/docs/reference/api/doxygen/functions_func_v.html b/docs/reference/api/doxygen/functions_func_v.html
index 6b33a7875..d0cd9038d 100644
--- a/docs/reference/api/doxygen/functions_func_v.html
+++ b/docs/reference/api/doxygen/functions_func_v.html
@@ -493,7 +493,7 @@ $(function() {
: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFrame.html#a8f8c990ee4fa7cb7472f5440f2ca3bde">tvm::runtime::vm::VMFrame</a>
</li>
<li>VMFunction()
-: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#aea763069fe1dd6849ce0d1ec336931e0">tvm::runtime::vm::VMFunction</a>
+: <a class="el" href="structtvm_1_1runtime_1_1vm_1_1VMFunction.html#af9d2bdcf19642c21bc4909b9e9b6196d">tvm::runtime::vm::VMFunction</a>
</li>
<li>Void()
: <a class="el" href="classtvm_1_1runtime_1_1DataType.html#ab8dc0832aff8fd7421884c0fe20a3bfd">tvm::runtime::DataType</a>
diff --git a/docs/reference/api/doxygen/functions_m.html b/docs/reference/api/doxygen/functions_m.html
index 63d1e1cf7..0f1d2c239 100644
--- a/docs/reference/api/doxygen/functions_m.html
+++ b/docs/reference/api/doxygen/functions_m.html
@@ -342,7 +342,7 @@ $(function() {
: <a class="el" href="classtvm_1_1DiagnosticContextNode.html#adea7e38a6e47cbab7fb5639f208aa536">tvm::DiagnosticContextNode</a>
</li>
<li>Module()
-: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abfbc619b3b3166d63ec52e399c24bed9">tvm::runtime::Module</a>
+: <a class="el" href="classtvm_1_1runtime_1_1Module.html#abd1380b3f813c2b6acefca3aaef425f4">tvm::runtime::Module</a>
, <a class="el" href="classtvm_1_1runtime_1_1ModuleNode.html#a21f639900c480510650969df9c74d17d">tvm::runtime::ModuleNode</a>
</li>
<li>module_handle
diff --git a/docs/reference/api/doxygen/functions_o.html b/docs/reference/api/doxygen/functions_o.html
index f8f9b0011..c24801a6b 100644
--- a/docs/reference/api/doxygen/functions_o.html
+++ b/docs/reference/api/doxygen/functions_o.html
@@ -383,7 +383,7 @@ $(function() {
, <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#aa6a6afa23fa3c3a81b3778f2869b3455">tvm::te::IterVarRelation</a>
, <a class="el" href="classtvm_1_1te_1_1Operation.html#a133e5d2639c0c657131b53c0877cdd79">tvm::te::Operation</a>
, <a class="el" href="classtvm_1_1te_1_1Schedule.html#a45d0647fe483156e98e76830db7c5130">tvm::te::Schedule</a>
-, <a class="el" href="classtvm_1_1te_1_1Stage.html#a7a5aeafe44281a6fca4b401139407241">tvm::te::Stage</a>
+, <a class="el" href="classtvm_1_1te_1_1Stage.html#a427ef4fef2edf15624be2c87bdad9505">tvm::te::Stage</a>
, <a class="el" href="classtvm_1_1tir_1_1Layout.html#a24d1414e53ab3bd153942bf5de5402e2">tvm::tir::Layout</a>
, <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ada44b624c1397c943ad9a0427378b048">tvm::tir::SizeVar</a>
, <a class="el" href="classtvm_1_1tir_1_1Var.html#a6a5db358f4fd7a9005a2d7a5f0fbe501">tvm::tir::Var</a>
@@ -412,13 +412,13 @@ $(function() {
: <a class="el" href="classtvm_1_1arith_1_1Analyzer.html#a9dccc7d98b8b9465390e10436d3a9178">tvm::arith::Analyzer</a>
, <a class="el" href="classtvm_1_1Integer.html#ad538a2ae6f636b3ce38fb4162b1c2549">tvm::Integer</a>
, <a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html#aef430b36a4be504969829f800e126245">tvm::relay::PatternWildcard</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a8f52fa8c97344586060ca735a3b91b39">tvm::runtime::Array< T, typename ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a5bc26222aa0257ece4c3a9d4d70fa1d8">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#ac62909410a98a078ff01f688cdf70ffe">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">tvm::runtime::Object</a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#afda3c65f41e83e1c87145a216f8c846d">tvm::runtime::ObjectPtr< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a377e159dbff53b8544a1b3337afc379d">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1String.html#a3b3c8614af05adc454f47132e04552ed">tvm::runtime::String</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#a5d251ed32af617354c8622689a6d6e48">tvm::runtime::TVMRetValue</a>
+, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#adf2a63e5560f521eef9a7bfda9994ffb">tvm::runtime::TVMRetValue</a>
... 4156 lines suppressed ...