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 2022/08/10 12:42:03 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@4280d673f193301816a201189c619370b1dd0f75)
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 8b702eedd deploying docs (apache/tvm@4280d673f193301816a201189c619370b1dd0f75)
8b702eedd is described below
commit 8b702eedddef2fef176acf27bfc2789dacebbd20
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Aug 10 12:41:57 2022 +0000
deploying docs (apache/tvm@4280d673f193301816a201189c619370b1dd0f75)
---
.../how_to/compile_models/from_coreml.rst.txt | 2 +-
.../how_to/compile_models/from_darknet.rst.txt | 4 +-
.../how_to/compile_models/from_mxnet.rst.txt | 4 +-
.../how_to/compile_models/from_oneflow.rst.txt | 4 +-
.../how_to/compile_models/from_onnx.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 4 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 4 +-
.../how_to/compile_models/from_tflite.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 4 +-
.../deploy_models/deploy_model_on_nano.rst.txt | 2 +-
.../deploy_models/deploy_model_on_rasp.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 6 +-
.../deploy_models/deploy_prequantized.rst.txt | 8 +-
.../deploy_prequantized_tflite.rst.txt | 6 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 4 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 6 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 14 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_infra.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 18 +-
.../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 | 2314 ++++++++++++--------
.../tune_network_arm.rst.txt | 2 +-
.../tune_network_cuda.rst.txt | 6 +-
.../tune_network_mali.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 8 +-
.../tune_sparse_x86.rst.txt | 22 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 40 +-
.../how_to/work_with_microtvm/micro_aot.rst.txt | 2 +-
.../work_with_microtvm/micro_autotune.rst.txt | 20 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/using_external_lib.rst.txt | 4 +-
.../using_pipeline_executor.rst.txt | 4 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../vta/tutorials/autotvm/tune_relay_vta.rst.txt | 2 +-
.../frontend/deploy_classification.rst.txt | 4 +-
.../tutorials/frontend/deploy_detection.rst.txt | 4 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/matrix_multiply.rst.txt | 2 +-
.../vta/tutorials/optimize/convolution_opt.rst.txt | 2 +-
.../tutorials/optimize/matrix_multiply_opt.rst.txt | 2 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/vta_get_started.rst.txt | 2 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 60 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/relay_quick_start.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 69 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_coreml.html | 2 +-
docs/how_to/compile_models/from_darknet.html | 4 +-
docs/how_to/compile_models/from_mxnet.html | 4 +-
docs/how_to/compile_models/from_oneflow.html | 18 +-
docs/how_to/compile_models/from_onnx.html | 2 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 4 +-
docs/how_to/compile_models/from_tflite.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 4 +-
.../how_to/deploy_models/deploy_model_on_nano.html | 2 +-
.../how_to/deploy_models/deploy_model_on_rasp.html | 2 +-
.../deploy_object_detection_pytorch.html | 51 +-
docs/how_to/deploy_models/deploy_prequantized.html | 10 +-
.../deploy_models/deploy_prequantized_tflite.html | 6 +-
docs/how_to/deploy_models/deploy_quantized.html | 4 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 41 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 14 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_infra.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 18 +-
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 | 2314 ++++++++++++--------
.../tune_with_autoscheduler/tune_network_arm.html | 2 +-
.../tune_with_autoscheduler/tune_network_cuda.html | 6 +-
.../tune_with_autoscheduler/tune_network_mali.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 8 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 22 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 40 +-
docs/how_to/work_with_microtvm/micro_aot.html | 2 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 20 +-
docs/how_to/work_with_microtvm/micro_train.html | 18 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/using_external_lib.html | 4 +-
.../work_with_relay/using_pipeline_executor.html | 4 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/driver.html | 3 +-
.../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 | 6 +-
.../vta/tutorials/autotvm/tune_relay_vta.html | 2 +-
.../tutorials/frontend/deploy_classification.html | 4 +-
.../vta/tutorials/frontend/deploy_detection.html | 4 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/matrix_multiply.html | 2 +-
.../vta/tutorials/optimize/convolution_opt.html | 2 +-
.../tutorials/optimize/matrix_multiply_opt.html | 2 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/vta_get_started.html | 2 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 264 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/relay_quick_start.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 65 +-
158 files changed, 3811 insertions(+), 2795 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_coreml.rst.txt b/docs/_sources/how_to/compile_models/from_coreml.rst.txt
index db6405001..78bdedb2a 100644
--- a/docs/_sources/how_to/compile_models/from_coreml.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_coreml.rst.txt
@@ -130,7 +130,7 @@ We should be familiar with the process right now.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 140f55eba..6ce95c378 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -165,7 +165,7 @@ compile the model
.. code-block:: none
Compiling the model...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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 6.369 seconds)
+ **Total running time of the script:** ( 1 minutes 9.816 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 e0d77995c..44f70be00 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.zipa6e16c62-fe36-48cd-900e-5d1b1515a350 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip26808a0f-291b-494d-a215-f2f2802c6efd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
@@ -166,7 +166,7 @@ now compile the graph
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 36109ba12..1c2c03e59 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]
19%|#9 | 7.99M/41.5M [00:00<00:00, 39.2MB/s]
38%|###7 | 15.7M/41.5M [00:00<00:00, 51.5MB/s]
51%|##### | 21.0M/41.5M [00:00<00:00, 52.7MB/s]
63%|######3 | 26.3M/41.5M [00:00<00:00, 38.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.3MB/s]
86%|########6 | 35.9M/41.5M [00:00<00:00, 36.6MB/s]
95%|#########5| 39.5M/41.5M [00:01<00:00, 25.6MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 33.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 50.4MB/s]
27%|##6 | 11.1M/41.5M [00:00<00:01, 29.9MB/s]
36%|###6 | 15.1M/41.5M [00:00<00:00, 33.5MB/s]
46%|####6 | 19.2M/41.5M [00:00<00:00, 36.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 29.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.6MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 21.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 27.5MB/s]
@@ -210,7 +210,7 @@ Compile the graph to llvm target with given input specification.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/compile_models/from_onnx.rst.txt b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
index 933a04240..b738ad059 100644
--- a/docs/_sources/how_to/compile_models/from_onnx.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_onnx.rst.txt
@@ -155,7 +155,7 @@ provides a static definition of the input size.
==> Context: Bad node spec for node. Name: OpType: Conv
warnings.warn(str(e))
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 384f8cbea..35287f6c4 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -168,7 +168,7 @@ Compile the model with relay
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 699fe9cf9..a04516f86 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]
39%|###9 | 17.5M/44.7M [00:00<00:00, 184MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 240MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 232MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
49%|####9 | 22.0M/44.7M [00:00<00:00, 231MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 259MB/s]
@@ -180,7 +180,7 @@ Compile the graph to llvm target with given input specification.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 1dc96b849..d2c29f003 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -264,7 +264,7 @@ Results:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.600 seconds)
+ **Total running time of the script:** ( 1 minutes 11.257 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/from_tflite.rst.txt b/docs/_sources/how_to/compile_models/from_tflite.rst.txt
index 29fc4f171..98019bcc1 100644
--- a/docs/_sources/how_to/compile_models/from_tflite.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tflite.rst.txt
@@ -222,7 +222,7 @@ Compile the model with relay
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 ef64be4db..eb052e994 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
=================
-**05:11.601** total execution time for **how_to_compile_models** files:
+**05:38.432** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.369 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.257 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.600 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.816 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.470 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:44.183 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.855 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:30.934 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.028 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.223 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:27.754 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:23.214 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:24.470 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.775 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.571 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.301 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.870 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.548 | 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 2b3ceaed3..8e15b6ca5 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
@@ -353,7 +353,7 @@ to run this tutorial with a real device.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2295 16.1601 16.6853 16.0297 0.1966
+ 17.0375 16.9110 17.6659 16.5938 0.4103
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_nano.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_nano.rst.txt
index e558ae353..61e53799a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_nano.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_nano.rst.txt
@@ -304,7 +304,7 @@ if you want to run this tutorial with a real device.
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt
index 16e736a37..4dd2d098e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_rasp.rst.txt
@@ -295,7 +295,7 @@ to run this tutorial with a real device.
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 1eb953f22..b5e0f1ba0 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]
3%|2 | 5.02M/170M [00:00<00:03, 52.3MB/s]
6%|5 | 10.0M/170M [00:00<00:07, 22.7MB/s]
9%|9 | 15.3M/170M [00:00<00:05, 31.4MB/s]
11%|#1 | 19.4M/170M [00:00<00:04, 34.4MB/s]
14%|#3 | 23.4M/170M [00:00<00:04, 34.0MB/s]
16%|#5 | 27.1M/170M [00:00<00:04, 34.3MB/s]
18%|#8 | 30.7M/170M [00:01<00:04, 30.0MB/s]
20%|#9 | 33.8M/170M [00:01<00:05, 27.1MB/s]
22%|##1 | 36.6M/170M [00:01<00:05, 25.5MB/s]
25%|##4 | 41.6M/170M [00:01<00:04, 32.0MB/s]
26%|##6 | 44.9M/170M [00:01<00:04, 32.5MB/s]
29%|##8 | 49.0M/170M [00:01<00:03, 35.1MB/s]
31%|### | 52.5M/170M [00:01<00:03, 34.4MB/s]
34%|###3 | 57.6M/170M [00:01<00:02, 39.7MB/s]
37%|###6 | 62.1M/170M [00:01<00:02, 41.6MB/s]
39%|###9 | 66.5M/170M [00:02<00:02, 41.3MB/s]
42%|####1 | 70.5M/170M [00:02<00:02, 36.5MB/
s]
45%|####4 | 76.2M/170M [00:02<00:02, 42.6MB/s]
47%|####7 | 80.4M/170M [00:02<00:02, 39.0MB/s]
50%|####9 | 84.3M/170M [00:02<00:02, 35.7MB/s]
53%|#####3 | 90.1M/170M [00:02<00:01, 41.9MB/s]
56%|#####6 | 95.5M/170M [00:02<00:01, 45.7MB/s]
59%|#####8 | 100M/170M [00:02<00:01, 46.7MB/s]
62%|######1 | 105M/170M [00:02<00:01, 46.1MB/s]
65%|######4 | 110M/170M [00:03<00:01, 47.0MB/s]
67%|######7 | 114M/170M [00:03<00:01, 46.2MB/s]
70%|######9 | 119M/170M [00:03<00:01, 35.9MB/s]
72%|#######2 | 123M/170M [00:03<00:01, 38.1MB/s]
75%|#######4 | 127M/170M [00:03<00:01, 32.4MB/s]
77%|#######6 | 130M/170M [00:03<00:01, 30.1MB/s]
79%|#######8 | 134M/170M [00:03<00:01, 31.4MB/s]
81%|######## | 137M/170M [00:04<00:01, 30.3MB/s]
84%|########3 | 143M/170M [00:04<00:00, 37.7MB/s]
87%|########7 | 148M/170M [00:04<00:00, 42.7MB/s]
90%|########9 | 152M/170M [00:04<00:00, 34.7MB/s
]
92%|#########1| 156M/170M [00:04<00:00, 34.7MB/s]
95%|#########5| 162M/170M [00:04<00:00, 40.3MB/s]
98%|#########7| 166M/170M [00:04<00:00, 40.8MB/s]
100%|##########| 170M/170M [00:04<00:00, 36.8MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|8 | 14.7M/170M [00:00<00:01, 152MB/s]
17%|#7 | 29.1M/170M [00:00<00:01, 101MB/s]
31%|### | 52.6M/170M [00:00<00:00, 153MB/s]
47%|####6 | 79.5M/170M [00:00<00:00, 196MB/s]
62%|######1 | 105M/170M [00:00<00:00, 220MB/s]
77%|#######7 | 131M/170M [00:00<00:00, 236MB/s]
92%|#########2| 157M/170M [00:00<00:00, 246MB/s]
100%|##########| 170M/170M [00:00<00:00, 212MB/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').
@@ -230,7 +230,7 @@ torchvision rcnn models.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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 5.418 seconds)
+ **Total running time of the script:** ( 3 minutes 5.996 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 cb3014dde..793b7ef0e 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]
40%|#### | 5.44M/13.6M [00:00<00:00, 56.5MB/s]
81%|########1 | 11.0M/13.6M [00:00<00:00, 56.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 44.9MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 160MB/s]
@@ -327,7 +327,7 @@ standard Relay operators before compilation.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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)
- 90.5174 90.4569 93.0623 90.1768 0.3247
+ 90.4170 90.3673 91.1995 90.2503 0.1515
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.339 seconds)
+ **Total running time of the script:** ( 1 minutes 11.399 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 0d3bb77aa..e5271096e 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
@@ -358,7 +358,7 @@ target platform that you are interested in.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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)
- 120.3960 120.1338 126.8454 119.1645 0.9981
+ 120.5655 120.4933 123.6882 119.5069 0.6241
@@ -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:** ( 1 minutes 59.298 seconds)
+ **Total running time of the script:** ( 1 minutes 59.252 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 a5b54db28..d72fc3304 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -244,7 +244,7 @@ We create a Relay VM to build and execute the model.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
@@ -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 42.744 seconds)
+ **Total running time of the script:** ( 1 minutes 42.680 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 ae7dd4621..44ce84923 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]
3%|2 | 3547/132723 [00:00<00:03, 35466.31KB/s]
7%|7 | 9782/132723 [00:00<00:02, 51275.72KB/s]
13%|#2 | 16632/132723 [00:00<00:01, 59132.68KB/s]
18%|#7 | 23529/132723 [00:00<00:01, 63009.75KB/s]
23%|##2 | 30120/132723 [00:00<00:01, 64050.47KB/s]
28%|##7 | 36526/132723 [00:00<00:01, 62964.98KB/s]
32%|###2 | 42875/132723 [00:00<00:01, 63132.07KB/s]
37%|###7 | 49757/132723 [00:00<00:01, 64927.26KB/s]
43%|####2 | 56552/132723 [00:00<00:01, 65865.67KB/s]
49%|####8 | 64557/132723 [00:01<00:00, 70170.89KB/s]
55%|#####4 | 72851/132723 [00:01<00:00, 74063.22KB/s]
61%|######1 | 81293/132723 [00:01<00:00, 77202.93KB/s]
67%|######7 | 89424/132723 [00:01<00:00, 78442.12KB/s]
74%|#######3 | 97663/132723 [00:01<00:00, 79630.41KB/s]
80%|#######9 | 106022/132723 [00:01<00:00, 80821.65KB/s]
86%|########6 |
114394/132723 [00:01<00:00, 81690.33KB/s]
93%|#########2| 122884/132723 [00:01<00:00, 82652.06KB/s]
99%|#########8| 131381/132723 [00:01<00:00, 83346.57KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72790.74KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6293/132723 [00:00<00:02, 62921.21KB/s]
11%|#1 | 14611/132723 [00:00<00:01, 74831.20KB/s]
17%|#6 | 22095/132723 [00:00<00:03, 36019.52KB/s]
20%|## | 27179/132723 [00:00<00:02, 35964.32KB/s]
25%|##4 | 32757/132723 [00:00<00:03, 30572.37KB/s]
30%|### | 40423/132723 [00:01<00:02, 39918.41KB/s]
37%|###6 | 48539/132723 [00:01<00:01, 49181.56KB/s]
42%|####2 | 56191/132723 [00:01<00:01, 55819.36KB/s]
49%|####8 | 64393/132723 [00:01<00:01, 62567.48KB/s]
55%|#####4 | 72633/132723 [00:01<00:00, 67896.51KB/s]
61%|###### | 80932/132723 [00:01<00:00, 72084.71KB/s]
67%|######7 | 88992/132723 [00:01<00:00, 74501.20KB/s]
73%|#######3 | 97085/132723 [00:01<00:00, 76354.47KB/s]
79%|#######9 | 105347/132723 [00:01<00:00, 78182.00KB/s]
86%|########5 | 113578/132723 [00:01<00:00, 79394.83KB/s]
92%|#########
1| 121652/132723 [00:02<00:00, 65789.11KB/s]
98%|#########7| 129902/132723 [00:02<00:00, 70106.56KB/s]
100%|##########| 132723/132723 [00:02<00:00, 59645.18KB/s]
@@ -203,7 +203,7 @@ Create TVM runtime and do inference
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 38.356 seconds)
+ **Total running time of the script:** ( 2 minutes 41.162 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 a44caeadb..ddfcac46a 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
=================
-**11:54.912** total execution time for **how_to_deploy_models** files:
+**12:01.057** 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``) | 03:05.418 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:05.996 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:38.356 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:41.162 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:59.298 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:59.252 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.744 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.680 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.339 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.399 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:32.060 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:32.859 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.347 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.075 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.355 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 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 9711bba44..f728bf7cc 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
@@ -147,7 +147,7 @@ Finally, we're ready to run the program:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
z: [0.7996937 1.168008 1.4516819]
@@ -414,7 +414,7 @@ while for all other operations, the bit length is the same between the operands
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
z: [0.7996937 1.168008 1.4516819]
x: [0.51729786 0.9469626 0.7654598 ]
@@ -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.zip4391d886-7d94-4143-80a2-9022470c245b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip572ef5d9-d3e1-4b14-83f7-d97ad0f1bbab from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -504,7 +504,7 @@ It's easy to execute MobileNet with native TVM:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
[ -7.5350165 2.0368009 -12.706646 -5.63786 -12.684058 4.0723605
2.618876 3.4049501 -9.867913 -24.53311 ]
@@ -588,9 +588,9 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
@@ -716,7 +716,7 @@ Now we can finally run the model:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
[ -7.5350165 2.0368009 -12.706646 -5.63786 -12.684058 4.0723605
2.618876 3.4049501 -9.867913 -24.53311 ]
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 897a7c5e6..c8e55307d 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
=================
-**00:42.016** total execution time for **how_to_extend_tvm** files:
+**00:42.731** 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``) | 00:38.731 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:39.422 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.299 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.307 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.978 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.995 | 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 |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt
index c422ed29c..889afc330 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_infra.rst.txt
@@ -138,7 +138,7 @@ Manually Apply Optimization Passes
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%0 = nn.conv2d(%x, %weight, padding=[0, 0, 0, 0]) /* ty=Tensor[(1, 64, 54, 54), float32] */;
@@ -282,7 +282,7 @@ pass.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%4 = fn (%p0: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %p1: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */, %p2: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, %p3: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, Primitive=1) -> Tensor[(1, 64, 54, 54), float32] {
@@ -327,7 +327,7 @@ for users to customize the optimization level that they want to execute.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%3 = fn (%p0: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %p1: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */, %p2: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, %p3: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, Primitive=1) -> Tensor[(1, 64, 54, 54), float32] {
@@ -371,7 +371,7 @@ identical addition operations.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%4 = fn (%p0: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %p1: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */, %p2: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, %p3: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, Primitive=1) -> Tensor[(1, 64, 54, 54), float32] {
@@ -561,7 +561,7 @@ a PassInsturment class printing IR before execution of each passes:
}
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Running pass: {} The meta data of the pass - pass name: InferType, opt_level: 0, required passes: []
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 939bb7531..dfb268f08 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: 6412us [6412us] (45.21%; 45.21%)
- FoldScaleAxis: 7772us [5us] (54.79%; 54.79%)
- FoldConstant: 7767us [1603us] (54.76%; 99.93%)
- InferType: 6164us [6164us] (43.46%; 79.36%)
+ InferType: 6763us [6763us] (45.71%; 45.71%)
+ FoldScaleAxis: 8032us [8us] (54.29%; 54.29%)
+ FoldConstant: 8023us [1616us] (54.23%; 99.90%)
+ InferType: 6407us [6407us] (43.31%; 79.86%)
@@ -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: 6172us [6172us] (44.59%; 44.59%)
- FoldScaleAxis: 7671us [5us] (55.41%; 55.41%)
- FoldConstant: 7666us [1595us] (55.38%; 99.94%)
- InferType: 6071us [6071us] (43.86%; 79.20%)
+ InferType: 6577us [6577us] (44.99%; 44.99%)
+ FoldScaleAxis: 8040us [7us] (55.01%; 55.01%)
+ FoldConstant: 8033us [1643us] (54.96%; 99.91%)
+ InferType: 6390us [6390us] (43.72%; 79.55%)
@@ -433,7 +433,7 @@ profile result.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 085557492..ec0f73c8a 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: 36.492911 ms
+ Convolution: 45.962045 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 6431db4cd..5c4ab2b56 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: 8.869483 ms
+ conv2d with tensor core: 10.577224 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 32e083d16..193d3a224 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: 0.018670
- Baseline: 3.236111
+ Numpy running time: 0.019591
+ Baseline: 3.369828
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.315768
+ Opt1: 0.322345
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.342657
+ Opt2: 0.347128
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120931
+ Opt3: 0.121079
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111174
+ Opt4: 0.112525
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111934
+ Opt5: 0.112953
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145182
+ Opt6: 0.146340
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 d70911faa..658d25530 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
=================
-**00:34.201** total execution time for **how_to_optimize_operators** files:
+**00:35.253** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.013 | 0.0 MB |
+| :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_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.212 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.369 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.976 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.086 | 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 015fc47b4..b0a08d4b2 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
=================
-**06:17.476** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:31.748** 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``) | 03:28.355 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:34.719 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.413 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:27.063 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:46.102 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:48.380 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:21.874 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:22.722 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.897 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.514 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.835 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.350 | 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 50b1d23d1..7ffe80f87 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
@@ -240,483 +240,745 @@ 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;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
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
- conv2d_nchw_1[1] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
- 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[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[11] = 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)
+ 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" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @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 + 336), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 24), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @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 + 1120), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @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 + 1232), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1344), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1456), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 60), 81)) && (floormod((threadIdx.x_1 + 60), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1680), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 10), 81)) && (floormod((threadIdx.x_1 + 10), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1792), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 41), 81)) && (floormod((threadIdx.x_1 + 41), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1904), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 41), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @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 + 2016), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 22), 81)) && (floormod((threadIdx.x_1 + 22), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2128), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 22), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2240), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @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 + 2464), 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" = 112;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2576), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[(threadIdx.x_2*16)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv((floormod(threadIdx.x_2, 18)*16), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 1), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 2), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 4)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 4), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 5), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 6)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 7), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 8)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 8), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 9)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 10)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 10), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 11)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 11), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 12)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 13)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 13), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 14)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 14), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 15)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1793)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 65), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1794)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 22), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1795)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1796)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 68), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1797)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 23), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1798)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1799)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 71), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1800)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 24), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1801)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1802)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 74), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1803)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 25), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1804)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1805)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 77), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1806)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 26), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1807)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3585)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 43), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3586)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 130), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3587)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3588)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 44), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3589)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 133), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3590)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3591)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 45), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3592)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 136), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3593)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3594)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 46), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3595)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 139), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3596)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3597)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 47), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3598)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 142), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3599)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 5376)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5377)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 193), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5378)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 194), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5379)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 65), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5380)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5381)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 197), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5382)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 66), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5383)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 199), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5384)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 200), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5385)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 67), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5386)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5387)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 203), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5388)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 68), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5389)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 205), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5390)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 206), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5391)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 69), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 7168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7169)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 257), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7170)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 86), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7171)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7172)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 260), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7173)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 87), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7174)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7175)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 263), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 88), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7177)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7178)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 266), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7179)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 89), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7180)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7181)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 269), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7182)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 90), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7183)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8961)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 11)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8962)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 34), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8963)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8964)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8965)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 37), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8966)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8967)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 13)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8968)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 40), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8969)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8970)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 14)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8971)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 43), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8972)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8973)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 15)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8974)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 46), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8975)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ for (ff.outer.inner: int32, 0, 2) {
+ let cse_var_8: int32 = (ff.outer.inner + 8)
+ let cse_var_7: int32 = (ff.outer.inner + 6)
+ let cse_var_6: int32 = (ff.outer.inner + 4)
+ let cse_var_5: int32 = (ff.outer.inner + 2)
+ let cse_var_4: int32 = (ff.outer.inner + 12)
+ let cse_var_3: int32 = (ff.outer.inner + 10)
+ {
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((rc.outer.inner*648) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 550)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 551)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 550)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 559)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 551)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 560)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 640)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 641)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
}
}
- 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 (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)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -771,7 +1033,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.353 ms
+ Execution time of this operator: 0.278 ms
@@ -821,34 +1083,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
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_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+ 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=7)
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_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
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_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)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
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_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
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_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_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
+ 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)
@@ -866,14 +1128,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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)
+ 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=16)
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=112)
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=112)
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, "unroll_explicit", True)
@@ -893,430 +1155,698 @@ 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) {
+ extern "C" __global__ void __launch_bounds__(112) 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];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[9216];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- 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[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 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);
+ 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) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((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) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 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) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((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) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((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) + 1232) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 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) + 1680)] = (((((9 <= ((((int)threadIdx.x) + 60) % 81)) && (((((int)threadIdx.x) + 60) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 81) * 49)) + ((((((int)threadIdx.x) + 60) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((9 <= ((((int)threadIdx.x) + 10) % 81)) && (((((int)threadIdx.x) + 10) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + ((((((int)threadIdx.x) + 10) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((9 <= ((((int)threadIdx.x) + 41) % 81)) && (((((int)threadIdx.x) + 41) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 81) * 49)) + ((((((int)threadIdx.x) + 41) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((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) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((9 <= ((((int)threadIdx.x) + 22) % 81)) && (((((int)threadIdx.x) + 22) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2128) / 81) * 49)) + ((((((int)threadIdx.x) + 22) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 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) + 2464)] = (((((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) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2576) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ }
+ kernel_shared[(((int)threadIdx.x) * 16)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) % 18) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 1) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 2) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 4)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 5) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 7) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 8)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 10)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 10) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 11)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 11) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 12)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 13)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 13) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 14)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 14) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 15)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 64) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1793)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 65) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1794)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 22) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1795)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1796)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 68) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1797)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 23) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1798)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1799)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 71) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 24) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1801)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1802)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 74) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1803)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 25) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1804)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1805)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 77) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1806)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 26) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1807)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 128) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3585)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 43) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3586)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 130) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3587)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3588)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 44) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3589)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 133) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3590)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3591)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 45) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3592)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 136) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3593)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3594)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 46) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3595)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 139) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3596)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3597)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 47) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3598)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 142) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3599)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5376)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5377)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 193) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5378)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 194) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5379)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 65) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5380)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5381)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 197) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5382)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 66) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5383)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 199) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5384)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 200) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5385)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 67) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5386)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 202) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5387)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 203) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5388)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 68) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5389)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 205) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5390)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 206) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5391)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 69) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7169)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 257) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7170)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 86) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7171)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7172)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 260) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7173)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 87) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7174)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7175)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 263) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 88) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7177)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7178)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 266) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7179)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 89) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7180)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7181)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 269) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7182)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 90) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7183)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8961)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 33)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8962)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 34) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8963)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8964)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 36)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8965)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 37) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8966)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8967)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 39)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8968)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8969)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8970)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 42)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8971)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 43) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8972)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8973)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 45)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8974)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 46) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8975)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((rc_outer_inner * 648) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 550)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 551)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 550)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 559)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 551)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 560)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 640)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 641)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
}
- 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 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);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1378,7 +1908,7 @@ 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 28.355 seconds)
+ **Total running time of the script:** ( 3 minutes 34.719 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_arm.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_arm.rst.txt
index 4e85b9ecb..7d075c50d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_arm.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_arm.rst.txt
@@ -331,7 +331,7 @@ The task scheduler will just optimize this objective.
Get model...
Extract tasks...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 b9ec04a5b..0a73ed97c 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
@@ -201,7 +201,7 @@ The task scheduler will just optimize this objective.
.. code-block:: none
Extract tasks...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 64], [1, 56, 56, 64]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -642,12 +642,12 @@ so we can read the log file and load the best schedules.
.. code-block:: none
Compile...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7941 9.8211 9.8446 9.7168 0.0555
+ 10.1545 10.1403 10.2062 10.1169 0.0378
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt
index 68360225f..595793a9a 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_mali.rst.txt
@@ -230,7 +230,7 @@ The task scheduler will just optimize this objective.
.. code-block:: none
Extract tasks...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 f3cc935f4..788660c72 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
@@ -224,7 +224,7 @@ The task scheduler will just optimize this objective.
Get model...
Extract tasks...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -661,12 +661,12 @@ so we can read the log file and load the best schedules.
.. code-block:: none
Compile...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.4837 752.7454 761.3244 749.3813 5.0283
+ 775.1436 774.3984 777.1445 773.8879 1.4301
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.413 seconds)
+ **Total running time of the script:** ( 1 minutes 27.063 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 579facdf3..4ccff9a55 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
@@ -397,13 +397,13 @@ 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_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), 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], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
+ for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
{
compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
@@ -424,11 +424,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
+ for (i.inner: int32, 0, 64) {
let cse_var_21: int32 = (elem_idx*16)
let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
let cse_var_17: int32 = (cse_var_18 + 9)
let cse_var_16: int32 = (cse_var_18 + 8)
let cse_var_15: int32 = (cse_var_18 + 7)
@@ -467,10 +467,8 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
- }
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -526,7 +524,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.730 ms
+ Execution time of this operator: 1.877 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 8fea3dcf8..98099cab5 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
=================
-**00:46.187** total execution time for **how_to_tune_with_autotvm** files:
+**00:47.100** 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``) | 00:46.151 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:47.068 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.016 | 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_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 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 1f401ee73..cf382d1e9 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
@@ -282,7 +282,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -405,7 +405,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -528,7 +528,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -651,7 +651,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -774,7 +774,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -897,7 +897,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1020,7 +1020,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1156,13 +1156,13 @@ 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: 80.79/80.79 result: MeasureResult(costs=(0.0028654588000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9271838665008545, timestamp=1660114072.9038901) [('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: 0.00/80.79 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 177.80/177.80 result: MeasureResult(costs=(0.0013020295666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.093247890472412, timestamp=1660131273.8314614) [('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: 0.00/177.80 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1280,13 +1280,13 @@ 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: 261.20/261.20 result: MeasureResult(costs=(0.0008862881491712708,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6869051456451416, timestamp=1660114073.8029814) [('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: 11 GFLOPS: 261.20/261.20 result: MeasureResult(costs=(0.0008863037458563535,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9330193996429443, timestamp=1660131274.872132) [('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: 0.00/261.20 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1409,7 +1409,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1532,7 +1532,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1650,8 +1650,8 @@ 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, 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: 5.31/261.20 result: MeasureResult(costs=(0.04355937375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8288960456848145, timestamp=1660114078.374904) [('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: 3.36/261.20 result: MeasureResult(costs=(0.06893701575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.56779932975769, timestamp=1660114079.6050844) [('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: 15 GFLOPS: 5.31/261.20 result: MeasureResult(costs=(0.043637877250000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8489155769348145, timestamp=1660131279.4905643) [('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: 3.35/261.20 result: MeasureResult(costs=(0.069205007,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.659145355224609, timestamp=1660131280.7657752) [('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: 0.00/261.20 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
@@ -1670,13 +1670,13 @@ 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: 28.17/261.20 result: MeasureResult(costs=(0.008219214357142858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2799923419952393, timestamp=1660114090.6589699) [('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: 18 GFLOPS: 27.32/261.20 result: MeasureResult(costs=(0.008474001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3466072082519531, timestamp=1660131291.8759305) [('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: 0.00/261.20 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1799,7 +1799,7 @@ for this template
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -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: 0.001254
+ Time cost of this operator: 0.001317
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt
index 2e7ff7959..754bf80e4 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_aot.rst.txt
@@ -168,7 +168,7 @@ Now, we compile the model for the target:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 bc46c141b..0e3504877 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
@@ -324,15 +324,15 @@ Timing the untuned program
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
########## 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 312.7 98.727 (1, 2, 10, 10, 3) 2 1 [312.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.067 0.968 (1, 6, 10, 10) 1 1 [3.067]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.304 (1, 1, 10, 10, 3) 1 1 [0.963]
- Total_time - 316.731 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 332.6 98.804 (1, 2, 10, 10, 3) 2 1 [332.6]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.048 0.905 (1, 6, 10, 10) 1 1 [3.048]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.979 0.291 (1, 1, 10, 10, 3) 1 1 [0.979]
+ Total_time - 336.627 - - - - -
@@ -393,15 +393,15 @@ Timing the tuned program
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
########## 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 79.312 96.587 (1, 6, 10, 10, 1) 2 1 [79.312]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.84 2.241 (1, 6, 10, 10) 1 1 [1.84]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 1.172 (1, 1, 10, 10, 3) 1 1 [0.962]
- Total_time - 82.115 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 88.938 96.988 (1, 6, 10, 10, 1) 2 1 [88.938]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.807 1.971 (1, 6, 10, 10) 1 1 [1.807]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 1.041 (1, 1, 10, 10, 3) 1 1 [0.955]
+ Total_time - 91.699 - - - - -
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 81d41d4a6..a34a34e66 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/tmpkk78cada/images/random'
+ '/tmp/tmpwe3sqvdo/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpkk78cada/images/target contains 8144 images
- /tmp/tmpkk78cada/images/random contains 5000 images
+ /tmp/tmpwe3sqvdo/images/target contains 8144 images
+ /tmp/tmpwe3sqvdo/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2200 - accuracy: 0.9264 - val_loss: 0.1369 - val_accuracy: 0.9581
+ 328/328 - 57s - loss: 0.2100 - accuracy: 0.9276 - val_loss: 0.1449 - val_accuracy: 0.9547
Epoch 2/3
- 328/328 - 52s - loss: 0.1032 - accuracy: 0.9616 - val_loss: 0.1184 - val_accuracy: 0.9615
+ 328/328 - 53s - loss: 0.0976 - accuracy: 0.9649 - val_loss: 0.1234 - val_accuracy: 0.9603
Epoch 3/3
- 328/328 - 52s - loss: 0.0660 - accuracy: 0.9759 - val_loss: 0.1038 - val_accuracy: 0.9649
+ 328/328 - 53s - loss: 0.0677 - accuracy: 0.9760 - val_loss: 0.1119 - val_accuracy: 0.9649
- <keras.callbacks.History object at 0x7f4225688510>
+ <keras.callbacks.History object at 0x7fa21c557c90>
@@ -681,7 +681,7 @@ Relay model into the MLF intermediate representation. From here, we just need to
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -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 8.196 seconds)
+ **Total running time of the script:** ( 5 minutes 41.494 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 05b52f4d4..6dc0a5e81 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
=================
-**06:04.416** total execution time for **how_to_work_with_microtvm** files:
+**06:39.883** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:08.196 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:41.494 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:44.338 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:46.039 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.533 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.733 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.346 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.615 | 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 ad6078829..1af0a913d 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
=================
-**00:42.949** total execution time for **how_to_work_with_relay** files:
+**00:43.229** 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``) | 00:31.415 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.768 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.945 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.943 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.583 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.510 | 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_relay/using_external_lib.rst.txt b/docs/_sources/how_to/work_with_relay/using_external_lib.rst.txt
index 643fe5be6..3a0883591 100644
--- a/docs/_sources/how_to/work_with_relay/using_external_lib.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/using_external_lib.rst.txt
@@ -127,7 +127,7 @@ By setting the logging level to DEBUG, the result of Relay graph compilation wil
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -570,7 +570,7 @@ To do that, all we need to do is to append the option " -libs=cudnn" to the targ
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/how_to/work_with_relay/using_pipeline_executor.rst.txt b/docs/_sources/how_to/work_with_relay/using_pipeline_executor.rst.txt
index 0b87e3cc4..ce6220a48 100644
--- a/docs/_sources/how_to/work_with_relay/using_pipeline_executor.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/using_pipeline_executor.rst.txt
@@ -359,7 +359,7 @@ Build the pipeline executor.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -476,7 +476,7 @@ Run these two subgraphs in sequence with graph_executor to get the output.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
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 706bf4147..f702518ba 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 0x7f4188dc1050>
+ <function my_cuda_math_rule at 0x7fa19017c950>
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 51ae52b11..3bd23f60b 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
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.178** total execution time for **how_to_work_with_schedules** files:
+**00:04.402** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.901 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.069 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.014 | 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``) | 00:00.578 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.556 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 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_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.026 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.016 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 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 eb9b43819..fed6421e6 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/tmpav3gf_o6/input0.cc'\nsource_filename = \"/tmp/tmpav3gf_o6/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/tmptlpubt_5/input0.cc'\nsource_filename = \"/tmp/tmptlpubt_5/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 100ecb414..41742398d 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
=================
-**00:22.139** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.269** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.133 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.263 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt
index f9d24ec81..7e453e20a 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/tune_relay_vta.rst.txt
@@ -536,7 +536,7 @@ Finally, we launch tuning jobs and evaluate the end-to-end performance.
.. code-block:: none
Extract tasks...
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/workspace/python/tvm/target/target.py:273: 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. "
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 bdf2ad699..d96fa027f 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -285,13 +285,13 @@ The compilation steps are:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
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 24.03s!
+ resnet18_v1 inference graph built in 24.23s!
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 71b1e6e39..89a6d4873 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -331,11 +331,11 @@ The compilation steps are:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.81s!
+ yolov3-tiny inference graph built in 16.80s!
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 76211bf6e..578316cf2 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
=================
-**01:33.979** total execution time for **topic_vta_tutorials_frontend** files:
+**01:35.021** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.739 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.265 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.240 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.756 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt b/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt
index fd2457a80..1975fd4af 100644
--- a/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/matrix_multiply.rst.txt
@@ -678,7 +678,7 @@ into a TVM function.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
index fa7858b3e..05b29797d 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/convolution_opt.rst.txt
@@ -914,7 +914,7 @@ ensure correctness.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Execution statistics:
inp_load_nbytes : 114688
diff --git a/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
index d8738e0b9..26290935e 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/matrix_multiply_opt.rst.txt
@@ -683,7 +683,7 @@ ensure correctness.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
Execution statistics:
inp_load_nbytes : 4096
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 3f1f51329..4828ff570 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
=================
-**00:03.300** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.312** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.884 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.861 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.415 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.450 | 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 8b0611380..bb51e6c00 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
=================
-**00:00.738** total execution time for **topic_vta_tutorials** files:
+**00:00.802** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.422 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.338 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.380 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt b/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
index ac5163c5b..3f087e925 100644
--- a/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/vta_get_started.rst.txt
@@ -555,7 +555,7 @@ we want to compile to.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 11baf8a7d..fb28b9e17 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -205,13 +205,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -335,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.385 ms
+ Execution time of this operator: 100.161 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 87a1e4240..44f852fb9 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: 10.68/10.68 result: MeasureResult(costs=(0.025131534,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5366127490997314, timestamp=1660112814.8317795) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.85/10.68 result: MeasureResult(costs=(0.094106117,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6591527462005615, timestamp=1660112816.5074644) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.89/11.89 result: MeasureResult(costs=(0.022569936999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5576667785644531, timestamp=1660112817.5565057) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.82/11.89 result: MeasureResult(costs=(0.14712051539999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.487107276916504, timestamp=1660112820.6377022) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.62/11.89 result: MeasureResult(costs=(0.074219207,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3120856285095215, timestamp=1660112822.0785651) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.74/11.89 result: MeasureResult(costs=(0.1545908622,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6289732456207275, timestamp=1660112824.7518473) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.89 result: MeasureResult(costs=(0.30805183080000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.058203935623169, timestamp=1660112830.37719) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.79/11.89 result: MeasureResult(costs=(0.024882658199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.540186882019043, timestamp=1660112830.9381738) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.92/11.89 result: MeasureResult(costs=(0.14005611759999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3483951091766357, timestamp=1660112833.4065702) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.78/11.89 result: MeasureResult(costs=(0.09641162480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6572589874267578, timestamp=1660112835.1177318) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.63/10.63 result: MeasureResult(costs=(0.0252604828,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5526022911071777, timestamp=1660129984.6606236) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.94/10.63 result: MeasureResult(costs=(0.09138427140000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6285014152526855, timestamp=1660129986.9025733) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 10.76/10.76 result: MeasureResult(costs=(0.024946087999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5921003818511963, timestamp=1660129988.0761607) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.84/10.76 result: MeasureResult(costs=(0.1461699324,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.470813751220703, timestamp=1660129990.5858896) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.58/10.76 result: MeasureResult(costs=(0.0750647296,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.350738525390625, timestamp=1660129992.0659351) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.74/10.76 result: MeasureResult(costs=(0.1541976488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.638409376144409, timestamp=1660129994.742962) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.86/10.76 result: MeasureResult(costs=(0.3109300364,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.10697340965271, timestamp=1660130000.4956524) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.64/10.76 result: MeasureResult(costs=(0.025239081400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.566070556640625, timestamp=1660130001.0715847) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.88/10.76 result: MeasureResult(costs=(0.14263357920000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3938844203948975, timestamp=1660130003.5864558) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.76/10.76 result: MeasureResult(costs=(0.0972611478,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.675722599029541, timestamp=1660130005.3146436) [('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 00bd99450..a1755f3db 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -253,7 +253,7 @@ runtime module from the library.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 498.93778268000005, 'median': 498.86395675000017, 'std': 1.4324142228454322}
+ {'mean': 501.45782568994036, 'median': 501.5043147497636, 'std': 0.917904139141461}
@@ -561,32 +561,32 @@ the tuning data to.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 17.51/ 17.51 GFLOPS | Progress: (4/20) | 6.46 s
[Task 1/25] Current/Best: 6.15/ 17.51 GFLOPS | Progress: (8/20) | 9.42 s
[Task 1/25] Current/Best: 11.51/ 22.88 GFLOPS | Progress: (12/20) | 11.92 s
[Task 1/25] Current/Best: 16.63/ 22.89 GFLOPS | Progress: (16/20) | 13.61 s
[Task 1/25] Current/Best: 11.60/ 23.64 GFLOPS | Progress: (20/20) | 15.36 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.34/ 12.87 GFLOPS | Progress: (4/20) | 3.97 s
[Task 2/25] Current/Best: 14.24/ 18.69 GFLOPS | Progress: (8/20) | 5.28 s
[Task 2/25] Current/Best: 20.71/ 20.71 GFLOPS | Progress: (12/20) | 6.60 s
[Task 2/25] Current/Best: 12.96/ 20.71 GFLOPS | Progress: (16/20) | 7.86 s
[Task 2/25] Current/Best: 18.90/ 20.71 GFLOPS | Progress: (20/20) | 9.48 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.49 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.52/ 16.91 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.88/ 16.91 GFLOPS | Progress: (12/20) | 9.58 s
[Task 3/25] Current/Best: 7.22/ 23.76 GFLOPS | Progress: (16/20) | 11.54 s
[Task 3/25] Current/Best: 12.64/ 23.76 GFLOPS | Progress: (20/20) | 16.16 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/ 20.41 GFLOPS | Progress: (4/20) | 2.43 s
[Task 4/25] Current/Best: 6.67/ 20.41 GFLOPS | Progress: (8/20) | 7.17 s
[Task 4/25] Current/Best: 20.84/ 20.84 GFLOPS | Progress: (12/20) | 12.11 s
[Task 4/25] Current/Best: 16.13/ 20.99 GFLOPS | Progress: (16/20) | 14.51 s
[Task 4/25] Current/Best: 13.48/ 20.99 GFLOPS | Progress: (20/20) | 16.51 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.85/ 10.41 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.91/ 12.78 GFLOPS | Progress: (8/20) | 4.74 s
[Task 5/25] Current/Best: 11.76/ 17.55 GFLOPS | Progress: (12/20) | 7.95 s
[Task 5/25] Current/Best: 11.87/ 22.59 GFLOPS | Progress: (16/20) | 9.39 s
[Task 5/25] Current/Best: 11.47/ 22.59 GFLOPS | Progress: (20/20) | 11.36 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.25/ 20.56 GFLOPS | Progress: (4/20) | 4.13 s
[Task 6/25] Current/Best: 18.94/ 20.56 GFLOPS | Progress: (8/20) | 5.89 s
[Task 6/25] Current/Best: 12.78/ 20.56 GFLOPS | Progress: (12/20) | 7.85 s
[Task 6/25] Current/Best: 19.95/ 20.56 GFLOPS | Progress: (16/20) | 10.10 s
[Task 6/25] Current/Best: 3.57/ 20.56 GFLOPS | Progress: (20/20) | 12.67 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.83/ 12.99 GFLOPS | Progress: (4/20) | 3.59 s
[Task 7/25] Current/Best: 20.21/ 20.67 GFLOPS | Progress: (8/20) | 5.13 s
[Task 7/25] Current/Best: 15.94/ 20.81 GFLOPS | Progress: (12/20) | 7.07 s
[Task 7/25] Current/Best: 12.17/ 20.81 GFLOPS | Progress: (16/20) | 9.15 s
[Task 7/25] Current/Best: 6.39/ 21.72 GFLOPS | Progress: (20/20) | 11.61 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.30/ 14.42 GFLOPS | Progress: (4/20) | 2.96 s
[Task 8/25] Current/Best: 10.30/ 14.42 GFLOPS | Progress: (8/20) | 8.06 s
[Task 8/25] Current/Best: 12.90/ 14.42 GFLOPS | Progress: (12/20) | 14.67 s
[Task 8/25] Current/Best: 18.60/ 18.60 GFLOPS | Progress: (16/20) | 16.74 s
[Task 8/25] Current/Best: 20.29/ 20.29 GFLOPS | Progress: (20/20) | 23.92 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.11/ 15.47 GFLOPS | Progress: (4/20) | 12.02 s
[Task 9/25] Current/Best: 23.40/ 23.40 GFLOPS | Progress: (8/20) | 13.83 s
[Task 9/25] Current/Best: 8.24/ 23.40 GFLOPS | Progress: (12/20) | 16.41 s
[Task 9/25] Current/Best: 17.95/ 23.40 GFLOPS | Progress: (16/20) | 19.20 s
[Task 9/25] Current/Best: 9.04/ 23.40 GFLOPS | Progress: (20/20) | 27.91 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 2.62 s
[Task 10/25] Current/Best: 15.25/ 18.22 GFLOPS | Progress: (8/20) | 4.26 s
[Task 10/25] Current/Best: 12.36/ 19.10 GFLOPS | Progress: (12/20) | 5.82 s
[Task 10/25] Current/Best: 19.14/ 20.51 GFLOPS | Progress: (16/20) | 6.95 s
[Task 10/25] Current/Best: 8.90/ 20.51 GFLOPS | Progress: (20/20
) | 8.49 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.34/ 18.12 GFLOPS | Progress: (4/20) | 3.36 s
[Task 11/25] Current/Best: 15.64/ 18.12 GFLOPS | Progress: (8/20) | 6.21 s
[Task 11/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (12/20) | 8.26 s
[Task 11/25] Current/Best: 13.50/ 21.20 GFLOPS | Progress: (16/20) | 11.18 s
[Task 11/25] Current/Best: 19.42/ 21.59 GFLOPS | Progress: (20/20) | 13.28 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.83/ 18.06 GFLOPS | Progress: (4/20) | 5.88 s
[Task 12/25] Current/Best: 4.96/ 18.06 GFLOPS | Progress: (8/20) | 9.92 s
[Task 12/25] Current/Best: 18.82/ 18.92 GFLOPS | Progress: (12/20) | 11.93 s
[Task 12/25] Current/Best: 15.40/ 18.92 GFLOPS | Progress: (16/20) | 14.93 s
[Task 12/25] Current/Best: 15.12/ 18.92 GFLOPS | Progress: (20/20) | 16.86 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.80/ 17.32 GFLOPS | Progress: (4/20) | 3.82 s
[Task 13/25] Current/Best: 16.12/ 21.04 GFLOPS | Progress: (8/20) | 6.44 s
[Task 13/25] Current/Best: 19.61/ 21.38 GFLOPS | Progress: (12/20) | 9.60 s
[Task 13/25] Current/Best: 12.25/ 21.38 GFLOPS | Progress: (16/20) | 13.09 s
[Task 13/25] Current/Best: 18.77/ 21.38 GFLOPS | Progress: (20/20) | 15.45 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) | 3.38 s
[Task 14/25] Current/Best: 6.12/ 13.73 GFLOPS | Progress: (8/20) | 5.56 s
[Task 14/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (12/20) | 8.21 s
[Task 14/25] Current/Best: 16.90/ 21.23 GFLOPS | Progress: (16/20) | 9.86 s Done.
-
[Task 14/25] Current/Best: 17.23/ 21.23 GFLOPS | Progress: (20/20) | 11.64 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.21/ 17.57 GFLOPS | Progress: (4/20) | 2.76 s
[Task 15/25] Current/Best: 14.29/ 17.82 GFLOPS | Progress: (8/20) | 4.12 s
[Task 15/25] Current/Best: 10.35/ 22.18 GFLOPS | Progress: (12/20) | 6.38 s
[Task 15/25] Current/Best: 20.15/ 22.18 GFLOPS | Progress: (16/20) | 9.56 s
[Task 15/25] Current/Best: 9.72/ 22.18 GFLOPS | Progress: (20/20) | 10.58 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.83/ 20.83 GFLOPS | Progress: (4/20) | 3.00 s
[Task 16/25] Current/Best: 3.02/ 20.83 GFLOPS | Progress: (8/20) | 4.61 s
[Task 16/25] Current/Best: 19.58/ 20.83 GFLOPS | Progress: (12/20) | 5.83 s
[Task 16/25] Current/Best: 17.89/ 20.83 GFLOPS | Progress: (16/20) |
7.20 s
[Task 16/25] Current/Best: 10.06/ 22.42 GFLOPS | Progress: (20/20) | 9.40 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.00/ 18.79 GFLOPS | Progress: (4/20) | 4.93 s
[Task 17/25] Current/Best: 14.45/ 23.07 GFLOPS | Progress: (8/20) | 7.84 s
[Task 17/25] Current/Best: 16.94/ 23.07 GFLOPS | Progress: (12/20) | 9.93 s
[Task 17/25] Current/Best: 16.42/ 23.07 GFLOPS | Progress: (16/20) | 12.14 s
[Task 17/25] Current/Best: 10.04/ 23.07 GFLOPS | Progress: (20/20) | 14.30 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.73/ 18.07 GFLOPS | Progress: (4/20) | 3.86 s
[Task 18/25] Current/Best: 10.57/ 18.07 GFLOPS | Progress: (8/20) | 7.62 s
[Task 18/25] Current/Best: 18.97/ 18.97 GFLOPS | Progress: (12/20) | 9.57 s
[Task 18/25] Current/Best: 10.08/ 18.97 GFLOPS | Progress: (16/20) | 13.44 s
[Task 18/25] Current/Best: 20.75/ 20.75 GFLOPS | Progress: (20/20) | 14.96 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.20/ 20.50 GFLOPS | Progress: (4/20) | 6.23 s
[Task 19/25] Current/Best: 2.60/ 20.50 GFLOPS | Progress: (8/20) | 9.60 s
[Task 19/25] Current/Best: 20.12/ 21.44 GFLOPS | Progress: (12/20) | 12.60 s
[Task 19/25] Current/Best: 15.37/ 21.44 GFLOPS | Progress: (16/20) | 15.63 s
[Task 19/25] Current/Best: 2.69/ 23.77 GFLOPS | Progress: (20/20) | 18.40 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.16/ 15.03 GFLOPS | Progress: (4/20) | 3.38 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 6.58 s
[Task 1/25] Current/Best: 6.16/ 17.39 GFLOPS | Progress: (8/20) | 9.57 s
[Task 1/25] Current/Best: 11.51/ 22.64 GFLOPS | Progress: (12/20) | 12.11 s
[Task 1/25] Current/Best: 16.77/ 22.67 GFLOPS | Progress: (16/20) | 13.81 s
[Task 1/25] Current/Best: 11.54/ 23.81 GFLOPS | Progress: (20/20) | 15.57 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.10/ 12.94 GFLOPS | Progress: (4/20) | 4.04 s
[Task 2/25] Current/Best: 14.30/ 18.53 GFLOPS | Progress: (8/20) | 5.36 s
[Task 2/25] Current/Best: 21.02/ 21.02 GFLOPS | Progress: (12/20) | 6.73 s
[Task 2/25] Current/Best: 12.96/ 21.02 GFLOPS | Progress: (16/20) | 8.01 s
[Task 2/25] Current/Best: 19.32/ 21.02 GFLOPS | Progress: (20/20) | 9.63 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.55 GFLOPS | Progress: (4/20) | 5.97 s
[Task 3/25] Current/Best: 15.51/ 16.78 GFLOPS | Progress: (8/20) | 7.93 s
[Task 3/25] Current/Best: 14.75/ 16.78 GFLOPS | Progress: (12/20) | 9.66 s
[Task 3/25] Current/Best: 7.13/ 23.59 GFLOPS | Progress: (16/20) | 11.60 s
[Task 3/25] Current/Best: 12.46/ 23.59 GFLOPS | Progress: (20/20) | 16.22 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.36 GFLOPS | Progress: (4/20) | 2.47 s
[Task 4/25] Current/Best: 6.82/ 20.36 GFLOPS | Progress: (8/20) | 7.26 s
[Task 4/25] Current/Best: 21.00/ 21.00 GFLOPS | Progress: (12/20) | 12.36 s
[Task 4/25] Current/Best: 17.01/ 21.00 GFLOPS | Progress: (16/20) | 14.80 s
[Task 4/25] Current/Best: 13.19/ 21.00 GFLOPS | Progress: (20/20) | 16.79 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.52/ 10.03 GFLOPS | Progress: (4/20) | 2.69 s
[Task 5/25] Current/Best: 11.67/ 13.15 GFLOPS | Progress: (8/20) | 4.78 s
[Task 5/25] Current/Best: 10.08/ 17.96 GFLOPS | Progress: (12/20) | 8.05 s
[Task 5/25] Current/Best: 11.79/ 22.22 GFLOPS | Progress: (16/20) | 9.52 s
[Task 5/25] Current/Best: 10.98/ 22.22 GFLOPS | Progress: (20/20) | 11.50 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.22/ 20.56 GFLOPS | Progress: (4/20) | 4.20 s
[Task 6/25] Current/Best: 18.81/ 20.56 GFLOPS | Progress: (8/20) | 5.97 s
[Task 6/25] Current/Best: 13.08/ 20.56 GFLOPS | Progress: (12/20) | 7.96 s
[Task 6/25] Current/Best: 19.68/ 20.56 GFLOPS | Progress: (16/20) | 10.24 s
[Task 6/25] Current/Best: 3.75/ 20.56 GFLOPS | Progress: (20/20) | 12.80 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.37/ 12.69 GFLOPS | Progress: (4/20) | 3.75 s
[Task 7/25] Current/Best: 20.02/ 20.99 GFLOPS | Progress: (8/20) | 5.30 s
[Task 7/25] Current/Best: 15.86/ 20.99 GFLOPS | Progress: (12/20) | 7.26 s
[Task 7/25] Current/Best: 12.26/ 20.99 GFLOPS | Progress: (16/20) | 9.34 s
[Task 7/25] Current/Best: 6.45/ 21.63 GFLOPS | Progress: (20/20) | 11.83 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.11/ 14.40 GFLOPS | Progress: (4/20) | 3.01 s
[Task 8/25] Current/Best: 9.88/ 14.40 GFLOPS | Progress: (8/20) | 8.20 s
[Task 8/25] Current/Best: 12.83/ 14.40 GFLOPS | Progress: (12/20) | 14.89 s
[Task 8/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 16.99 s
[Task 8/25] Current/Best: 19.60/ 19.60 GFLOPS | Progress: (20/20) | 24.17 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.04/ 15.63 GFLOPS | Progress: (4/20) | 12.03 s
[Task 9/25] Current/Best: 22.96/ 22.96 GFLOPS | Progress: (8/20) | 13.89 s
[Task 9/25] Current/Best: 8.20/ 22.96 GFLOPS | Progress: (12/20) | 16.44 s
[Task 9/25] Current/Best: 17.75/ 22.96 GFLOPS | Progress: (16/20) | 19.36 s
[Task 9/25] Current/Best: 9.05/ 22.96 GFLOPS | Progress: (20/20) | 28.04 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.46/ 18.46 GFLOPS | Progress: (4/20) | 2.67 s
[Task 10/25] Current/Best: 15.52/ 18.46 GFLOPS | Progress: (8/20) | 4.33 s
[Task 10/25] Current/Best: 12.76/ 19.20 GFLOPS | Progress: (12/20) | 5.91 s
[Task 10/25] Current/Best: 19.09/ 20.43 GFLOPS | Progress: (16/20) | 7.04 s
[Task 10/25] Current/Best: 8.98/ 20.43 GFLOPS | Progress: (20/20
) | 8.62 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.60/ 17.99 GFLOPS | Progress: (4/20) | 3.49 s
[Task 11/25] Current/Best: 16.75/ 17.99 GFLOPS | Progress: (8/20) | 6.34 s
[Task 11/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (12/20) | 8.41 s
[Task 11/25] Current/Best: 13.41/ 21.11 GFLOPS | Progress: (16/20) | 11.40 s
[Task 11/25] Current/Best: 19.37/ 21.45 GFLOPS | Progress: (20/20) | 13.52 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.79/ 18.13 GFLOPS | Progress: (4/20) | 5.88 s
[Task 12/25] Current/Best: 5.19/ 18.13 GFLOPS | Progress: (8/20) | 9.86 s
[Task 12/25] Current/Best: 19.27/ 19.27 GFLOPS | Progress: (12/20) | 11.86 s
[Task 12/25] Current/Best: 13.66/ 19.27 GFLOPS | Progress: (16/20) | 14.81 s
[Task 12/25] Current/Best: 15.16/ 19.36 GFLOPS | Progress: (20/20) | 16.80 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.91/ 17.26 GFLOPS | Progress: (4/20) | 3.86 s
[Task 13/25] Current/Best: 15.69/ 20.73 GFLOPS | Progress: (8/20) | 6.50 s
[Task 13/25] Current/Best: 19.44/ 21.00 GFLOPS | Progress: (12/20) | 9.70 s
[Task 13/25] Current/Best: 12.21/ 21.00 GFLOPS | Progress: (16/20) | 13.19 s
[Task 13/25] Current/Best: 18.15/ 21.00 GFLOPS | Progress: (20/20) | 15.48 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.52/ 13.52 GFLOPS | Progress: (4/20) | 3.57 s
[Task 14/25] Current/Best: 6.07/ 13.52 GFLOPS | Progress: (8/20) | 5.75 s
[Task 14/25] Current/Best: 20.68/ 20.68 GFLOPS | Progress: (12/20) | 8.44 s
[Task 14/25] Current/Best: 16.15/ 20.68 GFLOPS | Progress: (16/20) | 10.16 s Done.
+
[Task 14/25] Current/Best: 17.30/ 20.68 GFLOPS | Progress: (20/20) | 12.03 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.07/ 17.52 GFLOPS | Progress: (4/20) | 2.84 s
[Task 15/25] Current/Best: 14.34/ 17.85 GFLOPS | Progress: (8/20) | 4.16 s
[Task 15/25] Current/Best: 10.34/ 22.23 GFLOPS | Progress: (12/20) | 6.44 s
[Task 15/25] Current/Best: 20.27/ 22.23 GFLOPS | Progress: (16/20) | 9.65 s
[Task 15/25] Current/Best: 9.62/ 22.23 GFLOPS | Progress: (20/20) | 10.69 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (4/20) | 3.10 s
[Task 16/25] Current/Best: 3.04/ 20.51 GFLOPS | Progress: (8/20) | 4.76 s
[Task 16/25] Current/Best: 19.27/ 20.51 GFLOPS | Progress: (12/20) | 5.99 s
[Task 16/25] Current/Best: 17.69/ 20.51 GFLOPS | Progress: (16/20) |
7.38 s
[Task 16/25] Current/Best: 9.85/ 22.34 GFLOPS | Progress: (20/20) | 9.58 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.36/ 18.71 GFLOPS | Progress: (4/20) | 4.92 s
[Task 17/25] Current/Best: 14.41/ 22.96 GFLOPS | Progress: (8/20) | 7.77 s
[Task 17/25] Current/Best: 16.73/ 22.96 GFLOPS | Progress: (12/20) | 9.84 s
[Task 17/25] Current/Best: 17.35/ 22.96 GFLOPS | Progress: (16/20) | 12.08 s
[Task 17/25] Current/Best: 10.01/ 22.96 GFLOPS | Progress: (20/20) | 14.29 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.24/ 18.17 GFLOPS | Progress: (4/20) | 3.89 s
[Task 18/25] Current/Best: 10.57/ 20.01 GFLOPS | Progress: (8/20) | 7.63 s
[Task 18/25] Current/Best: 19.17/ 20.01 GFLOPS | Progress: (12/20) | 9.58 s
[Task 18/25] Current/Best: 9.84/ 20.01 GFLOPS | Progress: (16/20) | 13.49 s
[Task 18/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (20/20) | 15.02 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.29/ 20.09 GFLOPS | Progress: (4/20) | 6.49 s
[Task 19/25] Current/Best: 2.60/ 20.09 GFLOPS | Progress: (8/20) | 9.88 s
[Task 19/25] Current/Best: 19.27/ 20.80 GFLOPS | Progress: (12/20) | 12.86 s
[Task 19/25] Current/Best: 15.22/ 20.80 GFLOPS | Progress: (16/20) | 15.92 s
[Task 19/25] Current/Best: 2.70/ 23.17 GFLOPS | Progress: (20/20) | 18.72 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.02/ 14.89 GFLOPS | Progress: (4/20) | 3.48 s Done.
Done.
-
[Task 20/25] Current/Best: 9.73/ 15.03 GFLOPS | Progress: (8/20) | 6.98 s
[Task 20/25] Current/Best: 2.32/ 16.76 GFLOPS | Progress: (12/20) | 11.06 s
[Task 20/25] Current/Best: 12.41/ 16.76 GFLOPS | Progress: (16/20) | 14.86 s
[Task 20/25] Current/Best: 12.64/ 21.57 GFLOPS | Progress: (20/20) | 16.99 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.37/ 17.53 GFLOPS | Progress: (4/20) | 3.32 s
[Task 21/25] Current/Best: 14.46/ 17.53 GFLOPS | Progress: (8/20) | 4.95 s
[Task 21/25] Current/Best: 1.61/ 17.53 GFLOPS | Progress: (12/20) | 7.14 s
[Task 21/25] Current/Best: 17.84/ 17.84 GFLOPS | Progress: (16/20) | 10.73 s
[Task 21/25] Current/Best: 4.41/ 17.84 GFLOPS | Progress: (20/20) | 18.13 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.96 GFLOPS | Progress: (4/20
) | 2.75 s
[Task 22/25] Current/Best: 8.71/ 22.04 GFLOPS | Progress: (8/20) | 4.76 s
[Task 22/25] Current/Best: 20.05/ 22.04 GFLOPS | Progress: (12/20) | 7.19 s
[Task 22/25] Current/Best: 15.58/ 22.04 GFLOPS | Progress: (16/20) | 9.32 s
[Task 22/25] Current/Best: 15.00/ 22.04 GFLOPS | Progress: (20/20) | 11.09 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.26/ 20.41 GFLOPS | Progress: (4/20) | 3.36 s
[Task 23/25] Current/Best: 15.87/ 20.41 GFLOPS | Progress: (8/20) | 6.78 s
[Task 23/25] Current/Best: 20.78/ 21.20 GFLOPS | Progress: (12/20) | 8.62 s
[Task 23/25] Current/Best: 6.00/ 21.20 GFLOPS | Progress: (16/20) | 16.00 s
[Task 23/25] Current/Best: 6.52/ 21.20 GFLOPS | Progress: (20/20) | 20.35 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.61/ 8.61 GFLOPS | Progress: (4/20) | 11.83 s
[Task 24/25] Current/Best: 2.11/ 8.61 GFLOPS | Progress: (8/20) | 22.87 s
[Task 24/25] Current/Best: 4.68/ 8.61 GFLOPS | Progress: (12/20) | 34.45 s Done.
-
[Task 24/25] Current/Best: 6.80/ 8.89 GFLOPS | Progress: (16/20) | 40.22 s
[Task 24/25] Current/Best: 2.92/ 8.89 GFLOPS | Progress: (20/20) | 46.45 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/ 2.82 GFLOPS | Progress: (4/20) | 11.63 s
[Task 25/25] Current/Best: 5.77/ 8.07 GFLOPS | Progress: (8/20) | 22.96 s
[Task 25/25] Current/Best: 5.07/ 8.07 GFLOPS | Progress: (12/20) | 34.43 s
[Task 25/25] Current/Best: 5.15/ 9.52 GFLOPS | Progress: (16/20) | 36.20 s
[Task 25/25] Current/Best: 2.61/ 9.52 GFLOPS | Progress: (20/20) | 46.90 s
+
[Task 20/25] Current/Best: 10.35/ 14.89 GFLOPS | Progress: (8/20) | 6.93 s
[Task 20/25] Current/Best: 2.33/ 16.57 GFLOPS | Progress: (12/20) | 10.90 s
[Task 20/25] Current/Best: 12.49/ 16.57 GFLOPS | Progress: (16/20) | 14.75 s
[Task 20/25] Current/Best: 13.24/ 21.75 GFLOPS | Progress: (20/20) | 16.88 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.60 GFLOPS | Progress: (4/20) | 3.41 s
[Task 21/25] Current/Best: 14.40/ 17.60 GFLOPS | Progress: (8/20) | 4.99 s
[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 7.15 s
[Task 21/25] Current/Best: 18.08/ 18.08 GFLOPS | Progress: (16/20) | 10.78 s
[Task 21/25] Current/Best: 4.46/ 18.08 GFLOPS | Progress: (20/20) | 18.36 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20
) | 2.81 s
[Task 22/25] Current/Best: 9.15/ 21.40 GFLOPS | Progress: (8/20) | 4.79 s
[Task 22/25] Current/Best: 19.67/ 21.40 GFLOPS | Progress: (12/20) | 7.18 s
[Task 22/25] Current/Best: 15.08/ 21.40 GFLOPS | Progress: (16/20) | 9.36 s
[Task 22/25] Current/Best: 15.01/ 21.40 GFLOPS | Progress: (20/20) | 11.07 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.40/ 19.03 GFLOPS | Progress: (4/20) | 3.36 s
[Task 23/25] Current/Best: 15.64/ 19.47 GFLOPS | Progress: (8/20) | 6.88 s
[Task 23/25] Current/Best: 20.67/ 21.22 GFLOPS | Progress: (12/20) | 8.79 s
[Task 23/25] Current/Best: 5.81/ 21.22 GFLOPS | Progress: (16/20) | 16.18 s
[Task 23/25] Current/Best: 7.42/ 21.22 GFLOPS | Progress: (20/20) | 20.52 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.66/ 8.66 GFLOPS | Progress: (4/20) | 11.92 s
[Task 24/25] Current/Best: 2.03/ 8.66 GFLOPS | Progress: (8/20) | 23.04 s
[Task 24/25] Current/Best: 4.10/ 8.66 GFLOPS | Progress: (12/20) | 34.65 s Done.
+
[Task 24/25] Current/Best: 7.09/ 8.66 GFLOPS | Progress: (16/20) | 40.43 s
[Task 24/25] Current/Best: 3.23/ 8.86 GFLOPS | Progress: (20/20) | 46.55 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.51/ 2.43 GFLOPS | Progress: (4/20) | 11.71 s
[Task 25/25] Current/Best: 3.60/ 5.89 GFLOPS | Progress: (8/20) | 23.13 s
[Task 25/25] Current/Best: 4.99/ 5.89 GFLOPS | Progress: (12/20) | 34.73 s
[Task 25/25] Current/Best: 5.03/ 7.83 GFLOPS | Progress: (16/20) | 36.65 s
[Task 25/25] Current/Best: 2.41/ 7.83 GFLOPS | Progress: (20/20) | 47.40 s
@@ -655,7 +655,7 @@ model using optimized operators to speed up our computations.
.. code-block:: none
Done.
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 415.4607261000024, 'median': 414.8889504000067, 'std': 1.500784521798114}
- unoptimized: {'mean': 498.93778268000005, 'median': 498.86395675000017, 'std': 1.4324142228454322}
+ optimized: {'mean': 421.5538452299734, 'median': 421.614536999914, 'std': 0.6778321647184992}
+ unoptimized: {'mean': 501.45782568994036, 'median': 501.5043147497636, 'std': 0.917904139141461}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 34.426 seconds)
+ **Total running time of the script:** ( 10 minutes 42.934 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 1e852b726..4bf8df2ad 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
- 1.278e-07 secs/op
+ 1.245e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index bbd73206e..214e48234 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, 0xba02050)), stage(b, placeholder(b, 0x22c41590)), 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, 0x239aae70)), stage(b, placeholder(b, 0x2105b840)), 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(mi [...]
diff --git a/docs/_sources/tutorial/relay_quick_start.rst.txt b/docs/_sources/tutorial/relay_quick_start.rst.txt
index 64afcfe6c..2dd22fb61 100644
--- a/docs/_sources/tutorial/relay_quick_start.rst.txt
+++ b/docs/_sources/tutorial/relay_quick_start.rst.txt
@@ -259,7 +259,7 @@ in this example. Then the machine code will be generated as the module library.
/workspace/python/tvm/target/target.py:389: UserWarning: Try specifying cuda arch by adding 'arch=sm_xx' to your target.
warnings.warn("Try specifying cuda arch by adding 'arch=sm_xx' to your target.")
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index dbf1c635c..7e88a1f2f 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**13:29.985** total execution time for **tutorial** files:
+**13:44.362** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:34.426 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:42.934 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:59.907 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:08.654 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.839 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:54.050 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:30.881 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:32.369 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.788 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.569 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.254 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.842 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.720 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.748 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.159 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.185 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
@@ -30,7 +30,7 @@ Computation times
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.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_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.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 7a60d60a9..6ddd2d255 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -214,7 +214,7 @@ the inputs and outputs) as well as target language we want to compile to.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
@@ -301,8 +301,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000007
+ Numpy running time: 0.000007
+ naive: 0.000006
@@ -401,9 +401,9 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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. "
- parallel: 0.000006
+ parallel: 0.000007
@@ -458,7 +458,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.249059999343444e-06 1.0
- naive 6.691099999999999e-06 0.8111348445195641
- parallel 6.0724000000000005e-06 0.7361323593819554
- vector 2.4622400000000003e-05 2.9848734282402773
+ numpy 6.8236599690862935e-06 1.0
+ naive 5.8611000000000005e-06 0.858937875942376
+ parallel 6.9518999999999995e-06 1.0187934380515267
+ vector 2.45306e-05 3.5949329408459243
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018434
+ Numpy running time: 0.020142
@@ -994,9 +994,9 @@ optimizations.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 3.232418
+ none: 3.889314
@@ -1099,9 +1099,9 @@ schedule.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.308073
+ blocking: 0.337734
@@ -1197,9 +1197,9 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.340009
+ vectorization: 0.352818
@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], []),
@@ -1273,9 +1273,9 @@ more cache friendly.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.117527
+ loop permutation: 0.146876
@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], []),
@@ -1374,9 +1374,9 @@ optimized schedule.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.110379
+ array packing: 0.114028
@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], []),
@@ -1469,9 +1469,9 @@ to `C` when all the block results are ready.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.110959
+ block caching: 0.115946
@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], []),
@@ -1557,9 +1557,9 @@ of thread-level parallelization.
.. code-block:: none
- /workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+ /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: 0.145257
+ parallelization: 0.150482
@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 3.2324178162000003 1.0
- blocking 0.30807275230000003 0.09530721887375544
- vectorization 0.3400090568 0.10518722397085145
- loop permutation 0.11752707310000002 0.03635887431104551
- array packing 0.11037899209999999 0.03414750146061269
- block caching 0.1109585756 0.034326804859169426
- parallelization 0.1452566378 0.04493745736458114
+ none 3.8893144440999996 1.0
+ blocking 0.3377344322 0.08683649446558257
+ vectorization 0.35281762780000003 0.09071460610113853
+ loop permutation 0.1468759681 0.03776397362851632
+ array packing 0.1140277699 0.029318218297565913
+ block caching 0.11594606810000001 0.029811441004953334
+ parallelization 0.1504816781 0.038691054750864186
@@ -1686,6 +1686,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 8.654 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index e6042899d..168c47cbf 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-fae79bbc3e499f3b9f26c9a13743896f948b723d
+4280d673f193301816a201189c619370b1dd0f75
diff --git a/docs/how_to/compile_models/from_coreml.html b/docs/how_to/compile_models/from_coreml.html
index 0ad9b5ed3..d8cff6732 100644
--- a/docs/how_to/compile_models/from_coreml.html
+++ b/docs/how_to/compile_models/from_coreml.html
@@ -426,7 +426,7 @@ provided by apple in this example</p>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class="p">,</span> <a href="https://docs.python.org/3/library [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 8bf007a33..a41d69422 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -460,7 +460,7 @@ pip install opencv-python
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Compiling the model...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></div>
</div>
@@ -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 6.369 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.816 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 99fe65ec2..cc83d79b1 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.zipa6e16c62-fe36-48cd-900e-5d1b1515a350 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.zip26808a0f-291b-494d-a215-f2f2802c6efd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
@@ -450,7 +450,7 @@ We support MXNet static graph(symbol) and HybridBlock in mxnet.gluon</p>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">func</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class="p">,</span> <a href="https://docs.python.org/3/librar [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index 33eee2e8b..bd0fe3eb4 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,14 +432,14 @@ 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]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 39.2MB/s]
- 38%|###7 | 15.7M/41.5M [00:00<00:00, 51.5MB/s]
- 51%|##### | 21.0M/41.5M [00:00<00:00, 52.7MB/s]
- 63%|######3 | 26.3M/41.5M [00:00<00:00, 38.4MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 37.3MB/s]
- 86%|########6 | 35.9M/41.5M [00:00<00:00, 36.6MB/s]
- 95%|#########5| 39.5M/41.5M [00:01<00:00, 25.6MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 33.4MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 50.4MB/s]
+ 27%|##6 | 11.1M/41.5M [00:00<00:01, 29.9MB/s]
+ 36%|###6 | 15.1M/41.5M [00:00<00:00, 33.5MB/s]
+ 46%|####6 | 19.2M/41.5M [00:00<00:00, 36.4MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 29.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.6MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 21.5MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 27.5MB/s]
</pre></div>
</div>
</div>
@@ -497,7 +497,7 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class="o">=</span><a href="https://docs.python.org/3/library/ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_onnx.html b/docs/how_to/compile_models/from_onnx.html
index 1852f8657..4255e1407 100644
--- a/docs/how_to/compile_models/from_onnx.html
+++ b/docs/how_to/compile_models/from_onnx.html
@@ -451,7 +451,7 @@ provides a static definition of the input size.</p>
==> Context: Bad node spec for node. Name: OpType: Conv
warnings.warn(str(e))
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 19ab5a546..b8054663c 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -458,7 +458,7 @@ A quick solution is</p>
<span class="p">)</span><span class="o">.</span><span class="n">evaluate</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 0ccc93929..a23b1f3fe 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,8 @@ 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]
- 39%|###9 | 17.5M/44.7M [00:00<00:00, 184MB/s]
- 99%|#########8| 44.2M/44.7M [00:00<00:00, 240MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 232MB/s]
+ 49%|####9 | 22.0M/44.7M [00:00<00:00, 231MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 259MB/s]
</pre></div>
</div>
</div>
@@ -463,7 +462,7 @@ be unstable.</p>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="../../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class="o">=</span><a href="../../reference/api/py [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 93e4818a3..b91aade32 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -526,7 +526,7 @@ lib: target library which can be deployed on target with TVM runtime.</p>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="../../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class="p">,</span> <a href="https://docs.python.o [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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 3.600 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.257 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/from_tflite.html b/docs/how_to/compile_models/from_tflite.html
index 8a4f94b37..63db26a7e 100644
--- a/docs/how_to/compile_models/from_tflite.html
+++ b/docs/how_to/compile_models/from_tflite.html
@@ -495,7 +495,7 @@ flatc --python schema.fbs
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class="p">,</span> <a href="https://docs.python.org/3/library [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index ef9df175b..5a6b96df8 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>05:11.601</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:38.432</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>01:06.369</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>01:11.257</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>01:03.600</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>01:09.816</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>00:40.470</p></td>
+<td><p>00:44.183</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>00:28.855</p></td>
+<td><p>00:30.934</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:26.353</p></td>
+<td><p>00:28.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:25.223</p></td>
+<td><p>00:27.754</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>00:23.214</p></td>
+<td><p>00:24.470</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>00:19.775</p></td>
+<td><p>00:22.571</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>00:15.301</p></td>
+<td><p>00:16.870</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>00:02.442</p></td>
+<td><p>00:02.548</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 1bbdae2c7..1ebdf2c51 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -594,7 +594,7 @@ to run this tutorial with a real device.</p>
<span class="n">lib</span><span class="o">.</span><span class="n">export_library</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">lib_fname</span></a><span class="p">,</span> <span class="n">fcompile</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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)
- 16.2295 16.1601 16.6853 16.0297 0.1966
+ 17.0375 16.9110 17.6659 16.5938 0.4103
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_nano.html b/docs/how_to/deploy_models/deploy_model_on_nano.html
index a02e1684a..4f7868ce3 100644
--- a/docs/how_to/deploy_models/deploy_model_on_nano.html
+++ b/docs/how_to/deploy_models/deploy_model_on_nano.html
@@ -536,7 +536,7 @@ if you want to run this tutorial with a real device.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_rasp.html b/docs/how_to/deploy_models/deploy_model_on_rasp.html
index 9ac7b9380..0be3c6ffd 100644
--- a/docs/how_to/deploy_models/deploy_model_on_rasp.html
+++ b/docs/how_to/deploy_models/deploy_model_on_rasp.html
@@ -526,7 +526,7 @@ to run this tutorial with a real device.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
</pre></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 d5a3f78a3..c596d6968 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,45 +436,14 @@ 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]
- 3%|2 | 5.02M/170M [00:00<00:03, 52.3MB/s]
- 6%|5 | 10.0M/170M [00:00<00:07, 22.7MB/s]
- 9%|9 | 15.3M/170M [00:00<00:05, 31.4MB/s]
- 11%|#1 | 19.4M/170M [00:00<00:04, 34.4MB/s]
- 14%|#3 | 23.4M/170M [00:00<00:04, 34.0MB/s]
- 16%|#5 | 27.1M/170M [00:00<00:04, 34.3MB/s]
- 18%|#8 | 30.7M/170M [00:01<00:04, 30.0MB/s]
- 20%|#9 | 33.8M/170M [00:01<00:05, 27.1MB/s]
- 22%|##1 | 36.6M/170M [00:01<00:05, 25.5MB/s]
- 25%|##4 | 41.6M/170M [00:01<00:04, 32.0MB/s]
- 26%|##6 | 44.9M/170M [00:01<00:04, 32.5MB/s]
- 29%|##8 | 49.0M/170M [00:01<00:03, 35.1MB/s]
- 31%|### | 52.5M/170M [00:01<00:03, 34.4MB/s]
- 34%|###3 | 57.6M/170M [00:01<00:02, 39.7MB/s]
- 37%|###6 | 62.1M/170M [00:01<00:02, 41.6MB/s]
- 39%|###9 | 66.5M/170M [00:02<00:02, 41.3MB/s]
- 42%|####1 | 70.5M/170M [00:02<00:02, 36.5MB/s]
- 45%|####4 | 76.2M/170M [00:02<00:02, 42.6MB/s]
- 47%|####7 | 80.4M/170M [00:02<00:02, 39.0MB/s]
- 50%|####9 | 84.3M/170M [00:02<00:02, 35.7MB/s]
- 53%|#####3 | 90.1M/170M [00:02<00:01, 41.9MB/s]
- 56%|#####6 | 95.5M/170M [00:02<00:01, 45.7MB/s]
- 59%|#####8 | 100M/170M [00:02<00:01, 46.7MB/s]
- 62%|######1 | 105M/170M [00:02<00:01, 46.1MB/s]
- 65%|######4 | 110M/170M [00:03<00:01, 47.0MB/s]
- 67%|######7 | 114M/170M [00:03<00:01, 46.2MB/s]
- 70%|######9 | 119M/170M [00:03<00:01, 35.9MB/s]
- 72%|#######2 | 123M/170M [00:03<00:01, 38.1MB/s]
- 75%|#######4 | 127M/170M [00:03<00:01, 32.4MB/s]
- 77%|#######6 | 130M/170M [00:03<00:01, 30.1MB/s]
- 79%|#######8 | 134M/170M [00:03<00:01, 31.4MB/s]
- 81%|######## | 137M/170M [00:04<00:01, 30.3MB/s]
- 84%|########3 | 143M/170M [00:04<00:00, 37.7MB/s]
- 87%|########7 | 148M/170M [00:04<00:00, 42.7MB/s]
- 90%|########9 | 152M/170M [00:04<00:00, 34.7MB/s]
- 92%|#########1| 156M/170M [00:04<00:00, 34.7MB/s]
- 95%|#########5| 162M/170M [00:04<00:00, 40.3MB/s]
- 98%|#########7| 166M/170M [00:04<00:00, 40.8MB/s]
-100%|##########| 170M/170M [00:04<00:00, 36.8MB/s]
+ 9%|8 | 14.7M/170M [00:00<00:01, 152MB/s]
+ 17%|#7 | 29.1M/170M [00:00<00:01, 101MB/s]
+ 31%|### | 52.6M/170M [00:00<00:00, 153MB/s]
+ 47%|####6 | 79.5M/170M [00:00<00:00, 196MB/s]
+ 62%|######1 | 105M/170M [00:00<00:00, 220MB/s]
+ 77%|#######7 | 131M/170M [00:00<00:00, 236MB/s]
+ 92%|#########2| 157M/170M [00:00<00:00, 246MB/s]
+100%|##########| 170M/170M [00:00<00:00, 212MB/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').
@@ -538,7 +507,7 @@ torchvision rcnn models.</p>
<span class="n">vm_exec</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">vm</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span class= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -569,7 +538,7 @@ 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 5.418 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.996 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 6d3001624..49b98fbd8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,9 +480,7 @@ 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]
- 40%|#### | 5.44M/13.6M [00:00<00:00, 56.5MB/s]
- 81%|########1 | 11.0M/13.6M [00:00<00:00, 56.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 44.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 160MB/s]
</pre></div>
</div>
</div>
@@ -532,7 +530,7 @@ standard Relay operators before compilation.</p>
<span class="n">tvm_result</span><span class="p">,</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule" title="tvm.contrib.graph_executor.GraphModule" class="sphx-glr-backref-module-tvm-contrib-graph_executor sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">rt_mod</span></a> <span class="o">=</span> <span class="n">run_tvm_model</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a hr [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -571,7 +569,7 @@ 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)
- 90.5174 90.4569 93.0623 90.1768 0.3247
+ 90.4170 90.3673 91.1995 90.2503 0.1515
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +608,7 @@ 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 10.339 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.399 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 0e7c7441b..490f7ef77 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ target platform that you are interested in.</p>
<span class="n">lib</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build_module</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">target</span></a><span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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)
- 120.3960 120.1338 126.8454 119.1645 0.9981
+ 120.5655 120.4933 123.6882 119.5069 0.6241
</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> ( 1 minutes 59.298 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 59.252 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 1a2920f56..9651ca198 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -503,13 +503,13 @@ for calibration. But the accuracy might be impacted.</p>
<span class="n">main</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.744 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.680 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 2bab33285..9598a57d5 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]
- 3%|2 | 3547/132723 [00:00<00:03, 35466.31KB/s]
- 7%|7 | 9782/132723 [00:00<00:02, 51275.72KB/s]
- 13%|#2 | 16632/132723 [00:00<00:01, 59132.68KB/s]
- 18%|#7 | 23529/132723 [00:00<00:01, 63009.75KB/s]
- 23%|##2 | 30120/132723 [00:00<00:01, 64050.47KB/s]
- 28%|##7 | 36526/132723 [00:00<00:01, 62964.98KB/s]
- 32%|###2 | 42875/132723 [00:00<00:01, 63132.07KB/s]
- 37%|###7 | 49757/132723 [00:00<00:01, 64927.26KB/s]
- 43%|####2 | 56552/132723 [00:00<00:01, 65865.67KB/s]
- 49%|####8 | 64557/132723 [00:01<00:00, 70170.89KB/s]
- 55%|#####4 | 72851/132723 [00:01<00:00, 74063.22KB/s]
- 61%|######1 | 81293/132723 [00:01<00:00, 77202.93KB/s]
- 67%|######7 | 89424/132723 [00:01<00:00, 78442.12KB/s]
- 74%|#######3 | 97663/132723 [00:01<00:00, 79630.41KB/s]
- 80%|#######9 | 106022/132723 [00:01<00:00, 80821.65KB/s]
- 86%|########6 | 114394/132723 [00:01<00:00, 81690.33KB/s]
- 93%|#########2| 122884/132723 [00:01<00:00, 82652.06KB/s]
- 99%|#########8| 131381/132723 [00:01<00:00, 83346.57KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 72790.74KB/s]
+ 5%|4 | 6293/132723 [00:00<00:02, 62921.21KB/s]
+ 11%|#1 | 14611/132723 [00:00<00:01, 74831.20KB/s]
+ 17%|#6 | 22095/132723 [00:00<00:03, 36019.52KB/s]
+ 20%|## | 27179/132723 [00:00<00:02, 35964.32KB/s]
+ 25%|##4 | 32757/132723 [00:00<00:03, 30572.37KB/s]
+ 30%|### | 40423/132723 [00:01<00:02, 39918.41KB/s]
+ 37%|###6 | 48539/132723 [00:01<00:01, 49181.56KB/s]
+ 42%|####2 | 56191/132723 [00:01<00:01, 55819.36KB/s]
+ 49%|####8 | 64393/132723 [00:01<00:01, 62567.48KB/s]
+ 55%|#####4 | 72633/132723 [00:01<00:00, 67896.51KB/s]
+ 61%|###### | 80932/132723 [00:01<00:00, 72084.71KB/s]
+ 67%|######7 | 88992/132723 [00:01<00:00, 74501.20KB/s]
+ 73%|#######3 | 97085/132723 [00:01<00:00, 76354.47KB/s]
+ 79%|#######9 | 105347/132723 [00:01<00:00, 78182.00KB/s]
+ 86%|########5 | 113578/132723 [00:01<00:00, 79394.83KB/s]
+ 92%|#########1| 121652/132723 [00:02<00:00, 65789.11KB/s]
+ 98%|#########7| 129902/132723 [00:02<00:00, 70106.56KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 59645.18KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -487,7 +486,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">class_IDs</span><span class="p">,</span> <span class="n">scores</span><span class="p">,</span> <span class="n">bounding_boxs</span> <span class="o">=</span> <span class="n">run</span><span class="p">(</span><span class="n">lib</span><span class="p">,</span> <span class="n">dev</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -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 38.356 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 41.162 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 948b7c6a5..d0e73ae14 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>11:54.912</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>12:01.057</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</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>03:05.418</p></td>
+<td><p>03:05.996</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>02:38.356</p></td>
+<td><p>02:41.162</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>01:59.298</p></td>
+<td><p>01:59.252</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>01:42.744</p></td>
+<td><p>01:42.680</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>01:10.339</p></td>
+<td><p>01:11.399</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>00:32.060</p></td>
+<td><p>00:32.859</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>00:23.615</p></td>
+<td><p>00:24.347</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>00:23.075</p></td>
+<td><p>00:23.355</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>
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 48cf9a42e..1f04c1d4f 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -429,7 +429,7 @@ y: [0.28239584 0.22104536 0.6862221 ]
<span class="nb">print</span><span class="p">(</span><span class="s2">"z: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">z_output</span><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
z: [0.7996937 1.168008 1.4516819]
</pre></div>
@@ -569,7 +569,7 @@ while for all other operations, the bit length is the same between the operands
<span class="c1"># Perhaps as expected, the ``myfloat32`` results and ``float32`` are exactly the same!</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
z: [0.7996937 1.168008 1.4516819]
x: [0.51729786 0.9469626 0.7654598 ]
@@ -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.zip4391d886-7d94-4143-80a2-9022470c245b 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.zip572ef5d9-d3e1-4b14-83f7-d97ad0f1bbab 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>
@@ -623,7 +623,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="nb">print</span><span class="p">(</span><span class="n">result</span><span class="o">.</span><span class="n">flatten</span><span class="p">()[:</span><span class="mi">10</span><span class="p">])</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
[ -7.5350165 2.0368009 -12.706646 -5.63786 -12.684058 4.0723605
2.618876 3.4049501 -9.867913 -24.53311 ]
@@ -674,9 +674,9 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="nb">print</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
@@ -768,7 +768,7 @@ where the minimum representable custom datatype value is implemented using calls
<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_array_equal</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">result_myfloat</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
[ -7.5350165 2.0368009 -12.706646 -5.63786 -12.684058 4.0723605
2.618876 3.4049501 -9.867913 -24.53311 ]
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 173b8b44f..b7b9c609e 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>00:42.016</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:42.731</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</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>00:38.731</p></td>
+<td><p>00:39.422</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>00:02.299</p></td>
+<td><p>00:02.307</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>00:00.978</p></td>
+<td><p>00:00.995</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>
-<td><p>00:00.008</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/use_pass_infra.html b/docs/how_to/extend_tvm/use_pass_infra.html
index 02189d970..35400ab51 100644
--- a/docs/how_to/extend_tvm/use_pass_infra.html
+++ b/docs/how_to/extend_tvm/use_pass_infra.html
@@ -433,7 +433,7 @@ examples for each of them.</p>
<span class="nb">print</span><span class="p">(</span><span class="n">mod</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%0 = nn.conv2d(%x, %weight, padding=[0, 0, 0, 0]) /* ty=Tensor[(1, 64, 54, 54), float32] */;
@@ -522,7 +522,7 @@ pass.</p>
<span class="nb">print</span><span class="p">(</span><span class="n">mod1</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%4 = fn (%p0: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %p1: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */, %p2: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, %p3: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, Primitive=1) -> Tensor[(1, 64, 54, 54), float32] {
@@ -548,7 +548,7 @@ for users to customize the optimization level that they want to execute.</p>
<span class="nb">print</span><span class="p">(</span><span class="n">mod2</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%3 = fn (%p0: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %p1: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */, %p2: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, %p3: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, Primitive=1) -> Tensor[(1, 64, 54, 54), float32] {
@@ -572,7 +572,7 @@ identical addition operations.</p>
<span class="nb">print</span><span class="p">(</span><span class="n">mod3</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
def @main(%x: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %weight: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */) -> Tensor[(1, 64, 54, 54), float32] {
%4 = fn (%p0: Tensor[(1, 64, 56, 56), float32] /* ty=Tensor[(1, 64, 56, 56), float32] */, %p1: Tensor[(64, 64, 3, 3), float32] /* ty=Tensor[(64, 64, 3, 3), float32] */, %p2: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, %p3: Tensor[(1, 64, 54, 54), float32] /* ty=Tensor[(1, 64, 54, 54), float32] */, Primitive=1) -> Tensor[(1, 64, 54, 54), float32] {
@@ -709,7 +709,7 @@ def @main(%x: Tensor[(1, 64, 56, 56), float32], %weight: Tensor[(64, 64, 3, 3),
}
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
Running pass: {} The meta data of the pass - pass name: InferType, opt_level: 0, required passes: []
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 0cb92d390..d94880856 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: 6412us [6412us] (45.21%; 45.21%)
-FoldScaleAxis: 7772us [5us] (54.79%; 54.79%)
- FoldConstant: 7767us [1603us] (54.76%; 99.93%)
- InferType: 6164us [6164us] (43.46%; 79.36%)
+InferType: 6763us [6763us] (45.71%; 45.71%)
+FoldScaleAxis: 8032us [8us] (54.29%; 54.29%)
+ FoldConstant: 8023us [1616us] (54.23%; 99.90%)
+ InferType: 6407us [6407us] (43.31%; 79.86%)
</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: 6172us [6172us] (44.59%; 44.59%)
-FoldScaleAxis: 7671us [5us] (55.41%; 55.41%)
- FoldConstant: 7666us [1595us] (55.38%; 99.94%)
- InferType: 6071us [6071us] (43.86%; 79.20%)
+InferType: 6577us [6577us] (44.99%; 44.99%)
+FoldScaleAxis: 8040us [7us] (55.01%; 55.01%)
+ FoldConstant: 8033us [1643us] (54.96%; 99.91%)
+ InferType: 6390us [6390us] (43.72%; 79.55%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
@@ -664,7 +664,7 @@ profile result.</p>
<span class="c1"># print(profiles)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 4d3258d80..5f437ecca 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: 36.492911 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 45.962045 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 1c129ef23..251ee0a70 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: 8.869483 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.577224 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 ce3ca3821..e235c4885 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: 0.018670
-Baseline: 3.236111
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019591
+Baseline: 3.369828
</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: 0.315768
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.322345
</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: 0.342657
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347128
</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: 0.120931
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.121079
</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: 0.111174
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112525
</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: 0.111934
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112953
</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: 0.145182
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146340
</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 0200f970a..bab96843c 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>00:34.201</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.253</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>00:32.013</p></td>
+<td><p>00:32.798</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>00:01.212</p></td>
+<td><p>00:01.369</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>00:00.976</p></td>
+<td><p>00:01.086</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 04f1d354e..8c9862705 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>06:17.476</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:31.748</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>03:28.355</p></td>
+<td><p>03:34.719</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>01:23.413</p></td>
+<td><p>01:27.063</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>00:46.102</p></td>
+<td><p>00:48.380</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>00:21.874</p></td>
+<td><p>00:22.722</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>00:08.897</p></td>
+<td><p>00:09.514</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>00:08.835</p></td>
+<td><p>00:09.350</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 65328da1e..d32d99f93 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
@@ -491,483 +491,745 @@ 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;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
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
- conv2d_nchw_1[1] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
- 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[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[11] = 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 [...]
+ 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" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @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 + 336), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 672)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 24), 81)) && (floormod((threadIdx.x_1 + 24), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 672), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 24), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 5), 81)) && (floormod((threadIdx.x_1 + 5), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 896), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1008)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 4), 9)) && (floormod((threadIdx.x_1 + 36), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1008), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 4), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1120)] = @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 + 1120), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1232)] = @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 + 1232), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1344)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 48), 81)) && (floormod((threadIdx.x_1 + 48), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1344), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 48), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1456)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 79), 81)) && (floormod((threadIdx.x_1 + 79), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1456), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 79), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1680)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 60), 81)) && (floormod((threadIdx.x_1 + 60), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1680), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 60), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1792)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 10), 81)) && (floormod((threadIdx.x_1 + 10), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1792), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 1904)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 41), 81)) && (floormod((threadIdx.x_1 + 41), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1904), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 41), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2016)] = @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 + 2016), 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2128)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 22), 81)) && (floormod((threadIdx.x_1 + 22), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2128), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 22), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2240)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 53), 81)) && (floormod((threadIdx.x_1 + 53), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2240), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 53), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ 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" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 2464)] = @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 + 2464), 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" = 112;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 2576)] = @tir.if_then_else((((threadIdx.x_1 < 7) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2576), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 65), 81), 9)*7)) + (threadIdx.x_1 + 2)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[(threadIdx.x_2*16)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv((floormod(threadIdx.x_2, 18)*16), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 1), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 2)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 2), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 1), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 4)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 4), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 5), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 6)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 2), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 7), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 8)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 8), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 9)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 3), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 10)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 10), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 11)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 11), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 12)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 4), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 13)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 13), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 14)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floordiv(((floormod(threadIdx.x_2, 18)*16) + 14), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 15)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 5), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 64), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1793)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 65), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1794)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 22), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1795)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1796)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 68), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1797)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 23), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1798)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1799)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 71), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1800)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 24), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1801)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1802)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 74), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1803)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 25), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1804)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1805)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 77), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1806)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 26), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 1807)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 1792), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3585)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 43), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3586)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 130), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3587)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3588)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 44), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3589)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 133), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3590)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3591)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 45), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3592)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 136), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3593)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3594)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 46), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3595)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 139), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3596)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3597)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 47), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3598)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 142), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 3599)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 3584), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 5376)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 64), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5377)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 193), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5378)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 194), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5379)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 65), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5380)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5381)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 197), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5382)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 66), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5383)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 199), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5384)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 200), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5385)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 67), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5386)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5387)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 203), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5388)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 68), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5389)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 205), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5390)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 206), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 5391)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 69), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ kernel.shared_1[((threadIdx.x_2*16) + 7168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7169)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 257), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7170)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 86), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7171)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7172)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 260), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7173)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 87), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7174)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7175)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 263), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 88), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7177)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7178)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 266), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7179)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 89), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7180)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7181)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 269), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7182)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv((threadIdx.x_2*16), 3) + 90), 96)*3)) + floormod(threadIdx.x_2, 3))]
+ kernel.shared_1[((threadIdx.x_2*16) + 7183)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 7168), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 32), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8961)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 11)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8962)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 34), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8963)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 1), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8964)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8965)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 37), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8966)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 2), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8967)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 13)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8968)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 40), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8969)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 3), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8970)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 14)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8971)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 43), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8972)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 4), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8973)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + ((floordiv((threadIdx.x_2*16), 3) + 15)*3)) + floormod(threadIdx.x_2, 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8974)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floordiv(floormod(((threadIdx.x_2*16) + 46), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[((threadIdx.x_2*16) + 8975)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 18)*4608)) + cse_var_1) + (floormod((floordiv(((threadIdx.x_2*16) + 8960), 3) + 5), 96)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ }
+ for (rc.outer.inner: int32, 0, 4) {
+ for (ff.outer.inner: int32, 0, 2) {
+ let cse_var_8: int32 = (ff.outer.inner + 8)
+ let cse_var_7: int32 = (ff.outer.inner + 6)
+ let cse_var_6: int32 = (ff.outer.inner + 4)
+ let cse_var_5: int32 = (ff.outer.inner + 2)
+ let cse_var_4: int32 = (ff.outer.inner + 12)
+ let cse_var_3: int32 = (ff.outer.inner + 10)
+ {
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[((rc.outer.inner*648) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72))]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 1)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 2)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 3)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 4)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 5)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 6)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 7)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 8)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 9)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 10)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 11)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 12)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 13)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 14)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 15)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 16)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 17)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 18)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 19)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 20)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 21)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 22)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 23)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 24)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 25)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 26)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 27)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 28)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 29)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 30)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 31)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 32)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 33)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 34)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 35)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 36)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 37)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 38)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 39)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 40)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 41)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 351)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 360)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 369)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 387)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 396)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 42)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 352)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 361)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 370)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 388)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 397)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 43)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 353)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 362)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 371)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 389)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 398)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 44)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 45)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 46)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 47)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 48)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 49)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 50)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 432)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 450)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 459)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 468)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 477)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 51)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 433)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 451)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 460)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 478)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 52)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 434)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 452)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 461)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 470)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 479)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 53)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 54)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 55)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 56)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 57)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 550)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 58)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 551)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 59)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 513)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 522)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 531)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 540)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 549)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 558)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 60)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 514)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 523)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 541)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 550)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 559)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 61)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 515)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 524)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 533)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 542)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 551)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 560)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 62)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 63)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 64)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 65)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 66)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 67)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 68)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 594)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 603)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 612)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 621)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 639)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 69)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 604)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 613)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 622)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 640)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 70)]))
+ conv2d_nchw_1[ff.outer.inner] = (conv2d_nchw_1[ff.outer.inner] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 596)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 605)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 614)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 623)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
+ conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.outer.inner*648) + floormod(threadIdx.x, 7)) + 641)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ff.outer.inner*288)) + (rc.outer.inner*72)) + 71)]))
}
}
- 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 (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)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 7)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 14)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 21)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 28)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 35)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 7)) + 42)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1004,7 +1266,7 @@ 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: 0.353 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.278 ms
</pre></div>
</div>
</div>
@@ -1035,34 +1297,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
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_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
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_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+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=7)
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_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
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_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)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, 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_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
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_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_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
+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)
@@ -1080,14 +1342,14 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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)
+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=16)
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=112)
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=112)
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, "unroll_explicit", True)
@@ -1107,430 +1369,698 @@ 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) {
+extern "C" __global__ void __launch_bounds__(112) 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];
+ __shared__ float pad_temp_shared[2592];
+ __shared__ float kernel_shared[9216];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- 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[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 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);
+ 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) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((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) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 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) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((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) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((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) + 1232) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((9 <= ((((int)threadIdx.x) + 48) % 81)) && (((((int)threadIdx.x) + 48) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1344) / 81) * 49)) + ((((((int)threadIdx.x) + 48) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((9 <= ((((int)threadIdx.x) + 79) % 81)) && (((((int)threadIdx.x) + 79) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1456) / 81) * 49)) + ((((((int)threadIdx.x) + 79) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 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) + 1680)] = (((((9 <= ((((int)threadIdx.x) + 60) % 81)) && (((((int)threadIdx.x) + 60) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1680) / 81) * 49)) + ((((((int)threadIdx.x) + 60) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((9 <= ((((int)threadIdx.x) + 10) % 81)) && (((((int)threadIdx.x) + 10) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1792) / 81) * 49)) + ((((((int)threadIdx.x) + 10) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((9 <= ((((int)threadIdx.x) + 41) % 81)) && (((((int)threadIdx.x) + 41) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1904) / 81) * 49)) + ((((((int)threadIdx.x) + 41) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((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) + 2016) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((9 <= ((((int)threadIdx.x) + 22) % 81)) && (((((int)threadIdx.x) + 22) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2128) / 81) * 49)) + ((((((int)threadIdx.x) + 22) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((9 <= ((((int)threadIdx.x) + 53) % 81)) && (((((int)threadIdx.x) + 53) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2240) / 81) * 49)) + ((((((int)threadIdx.x) + 53) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 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) + 2464)] = (((((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) + 2464) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 2576)] = ((((((int)threadIdx.x) < 7) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2576) / 81) * 49)) + (((((int)threadIdx.x) + 65) / 9) * 7)) + ((int)threadIdx.x)) - 6)] : 0.000000e+00f);
+ }
+ kernel_shared[(((int)threadIdx.x) * 16)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) % 18) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 1) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 2)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 2) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 1) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 4)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 4) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 5) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 6)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 2) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 7) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 8)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 9)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 3) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 10)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 10) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 11)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 11) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 12)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 4) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 13)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 13) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 14)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) % 18) * 16) + 14) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 15)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 5) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 64) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1793)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 65) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1794)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 22) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1795)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1796)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 68) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1797)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 23) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1798)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1799)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 71) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 24) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1801)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1802)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 74) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1803)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 25) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1804)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1805)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 77) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1806)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 26) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 1807)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 1792) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 128) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3585)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 43) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3586)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 130) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3587)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3588)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 44) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3589)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 133) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3590)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3591)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 45) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3592)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 136) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3593)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3594)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 46) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3595)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 139) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3596)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3597)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 47) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3598)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 142) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 3599)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 3584) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5376)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 64) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5377)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 193) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5378)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 194) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5379)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 65) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5380)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5381)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 197) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5382)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 66) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5383)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 199) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5384)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 200) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5385)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 67) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5386)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 202) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5387)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 203) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5388)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 68) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5389)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 205) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5390)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 206) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 5391)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 69) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7169)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 257) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7170)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 86) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7171)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7172)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 260) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7173)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 87) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7174)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7175)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 263) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 88) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7177)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7178)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 266) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7179)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 89) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7180)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7181)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) + 269) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7182)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((((int)threadIdx.x) * 16) / 3) + 90) % 96) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[((((int)threadIdx.x) * 16) + 7183)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 7168) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8961)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 33)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8962)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 34) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8963)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 1) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8964)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 36)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8965)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 37) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8966)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 2) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8967)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 39)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8968)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8969)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 3) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8970)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 42)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8971)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 43) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8972)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 4) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8973)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) * 16) / 3) * 3)) + (((int)threadIdx.x) % 3)) + 45)];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8974)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) * 16) + 46) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[((((int)threadIdx.x) * 16) + 8975)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 18) * 4608)) + (rc_outer_outer * 288)) + ((((((((int)threadIdx.x) * 16) + 8960) / 3) + 5) % 96) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[((rc_outer_inner * 648) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72))]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 1)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 2)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 3)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 4)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 5)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 6)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 7)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 8)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 9)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 10)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 11)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 12)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 13)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 14)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 15)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 16)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 17)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 18)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 19)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 20)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 21)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 22)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 23)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 24)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 25)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 26)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 27)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 28)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 29)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 30)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 31)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 32)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 33)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 34)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 35)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 36)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 37)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 38)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 39)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 40)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 41)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 42)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 43)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 44)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 45)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 46)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 47)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 48)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 49)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 50)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 51)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 52)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 53)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 54)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 55)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 56)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 57)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 550)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 58)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 551)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 59)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 513)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 522)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 531)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 540)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 549)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 558)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 60)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 514)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 523)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 541)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 550)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 559)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 61)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 515)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 524)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 533)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 542)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 551)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 560)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 62)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 63)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 64)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 65)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 66)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 67)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 68)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 594)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 603)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 612)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 621)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 639)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 69)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 604)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 613)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 622)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 640)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 70)]));
+ conv2d_nchw[ff_outer_inner] = (conv2d_nchw[ff_outer_inner] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 2)] = (conv2d_nchw[(ff_outer_inner + 2)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 596)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 4)] = (conv2d_nchw[(ff_outer_inner + 4)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 605)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 6)] = (conv2d_nchw[(ff_outer_inner + 6)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 614)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 8)] = (conv2d_nchw[(ff_outer_inner + 8)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 623)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 10)] = (conv2d_nchw[(ff_outer_inner + 10)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
+ conv2d_nchw[(ff_outer_inner + 12)] = (conv2d_nchw[(ff_outer_inner + 12)] + (pad_temp_shared[(((rc_outer_inner * 648) + (((int)threadIdx.x) % 7)) + 641)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ff_outer_inner * 288)) + (rc_outer_inner * 72)) + 71)]));
}
- 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 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);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 7)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 14)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 21)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 28)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 35)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 7)) + 42)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1567,7 +2097,7 @@ 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 28.355 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 34.719 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_arm.html b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
index 3c823d032..e49a87257 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_arm.html
@@ -602,7 +602,7 @@ The task scheduler will just optimize this objective.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get model...
Extract tasks...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 74166c6ee..9f10faf24 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -500,7 +500,7 @@ The task scheduler will just optimize this objective.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Extract tasks...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 64], [1, 56, 56, 64]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -901,12 +901,12 @@ so we can read the log file and load the best schedules.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Compile...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7941 9.8211 9.8446 9.7168 0.0555
+ 10.1545 10.1403 10.2062 10.1169 0.0378
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
index 32f90ed6c..eaa065a0e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_mali.html
@@ -515,7 +515,7 @@ The task scheduler will just optimize this objective.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Extract tasks...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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 0 (workload key: ["1037be767e8e18197e87653d81c34558", [1, 7, 7, 1024], [1, 1, 1024, 1024], [1, 1, 1, 1024], [1, 7, 7, 1024]]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 1024]
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 f2e34c79f..0e1773f8c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -523,7 +523,7 @@ The task scheduler will just optimize this objective.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get model...
Extract tasks...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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 0 (workload key: ["8654f16aeddf785bad9f028164b3a48d", [1, 56, 56, 64], [1, 1, 64, 256], [1, 56, 56, 256]]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
@@ -920,12 +920,12 @@ so we can read the log file and load the best schedules.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Compile...
-/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+/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. "
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.4837 752.7454 761.3244 749.3813 5.0283
+ 775.1436 774.3984 777.1445 773.8879 1.4301
</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 23.413 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.063 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 78cd6ef9e..13c55bd92 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,13 +625,13 @@ 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_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), 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], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
+ for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+ for (i.inner.init: int32, 0, 64) {
+ let cse_var_1: int32 = (((i.outer.inner*2048) + (i.inner.init*32)) + (nb_j.inner*16))
{
compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
compute_5[(cse_var_1 + 1)] = 0f32
@@ -652,11 +652,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
+ for (i.inner: int32, 0, 64) {
let cse_var_21: int32 = (elem_idx*16)
let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((i.outer.inner*16384) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*2048) + (i.inner*32)) + (nb_j.inner*16))
let cse_var_17: int32 = (cse_var_18 + 9)
let cse_var_16: int32 = (cse_var_18 + 8)
let cse_var_15: int32 = (cse_var_18 + 7)
@@ -695,10 +695,8 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
- }
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -736,7 +734,7 @@ 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: 1.730 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.877 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 653f25766..b6550209d 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>00:46.187</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:47.100</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>00:46.151</p></td>
+<td><p>00:47.068</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>00:00.020</p></td>
+<td><p>00:00.016</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>00:00.006</p></td>
+<td><p>00:00.005</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 0774747d7..aa0a4049f 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -562,7 +562,7 @@ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -685,7 +685,7 @@ No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -808,7 +808,7 @@ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -931,7 +931,7 @@ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1054,7 +1054,7 @@ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1177,7 +1177,7 @@ No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1300,7 +1300,7 @@ No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1436,13 +1436,13 @@ 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: 80.79/80.79 result: MeasureResult(costs=(0.0028654588000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9271838665008545, timestamp=1660114072.9038901) [('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: 0.00/80.79 result: Traceback (most recent call last):
+No: 9 GFLOPS: 177.80/177.80 result: MeasureResult(costs=(0.0013020295666666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.093247890472412, timestamp=1660131273.8314614) [('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: 0.00/177.80 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1560,13 +1560,13 @@ 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: 261.20/261.20 result: MeasureResult(costs=(0.0008862881491712708,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6869051456451416, timestamp=1660114073.8029814) [('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: 11 GFLOPS: 261.20/261.20 result: MeasureResult(costs=(0.0008863037458563535,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9330193996429443, timestamp=1660131274.872132) [('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: 0.00/261.20 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1689,7 +1689,7 @@ No: 13 GFLOPS: 0.00/261.20 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1812,7 +1812,7 @@ No: 14 GFLOPS: 0.00/261.20 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -1930,8 +1930,8 @@ 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, 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: 5.31/261.20 result: MeasureResult(costs=(0.04355937375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8288960456848145, timestamp=1660114078.374904) [('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: 3.36/261.20 result: MeasureResult(costs=(0.06893701575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.56779932975769, timestamp=1660114079.6050844) [('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: 15 GFLOPS: 5.31/261.20 result: MeasureResult(costs=(0.043637877250000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8489155769348145, timestamp=1660131279.4905643) [('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: 3.35/261.20 result: MeasureResult(costs=(0.069205007,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.659145355224609, timestamp=1660131280.7657752) [('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: 0.00/261.20 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
@@ -1950,13 +1950,13 @@ No: 17 GFLOPS: 0.00/261.20 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: 28.17/261.20 result: MeasureResult(costs=(0.008219214357142858,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2799923419952393, timestamp=1660114090.6589699) [('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: 18 GFLOPS: 27.32/261.20 result: MeasureResult(costs=(0.008474001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3466072082519531, timestamp=1660131291.8759305) [('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: 0.00/261.20 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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -2079,7 +2079,7 @@ No: 20 GFLOPS: 0.00/261.20 result: Traceback (most recent call last):
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
func = build(s, args, target_host=task.target_host, runtime=runtime)
- File "/workspace/python/tvm/driver/build_module.py", line 228, in build
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
@@ -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: 0.001254
+Time cost of this operator: 0.001317
</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_aot.html b/docs/how_to/work_with_microtvm/micro_aot.html
index fecf932fc..cc68d12a6 100644
--- a/docs/how_to/work_with_microtvm/micro_aot.html
+++ b/docs/how_to/work_with_microtvm/micro_aot.html
@@ -454,7 +454,7 @@ micro target.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index b07301338..1a7a69f71 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -579,15 +579,15 @@ the tuned operator.</p>
<span class="k">del</span> <span class="n">debug_module</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
########## 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 312.7 98.727 (1, 2, 10, 10, 3) 2 1 [312.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.067 0.968 (1, 6, 10, 10) 1 1 [3.067]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.304 (1, 1, 10, 10, 3) 1 1 [0.963]
-Total_time - 316.731 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 332.6 98.804 (1, 2, 10, 10, 3) 2 1 [332.6]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.048 0.905 (1, 6, 10, 10) 1 1 [3.048]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.979 0.291 (1, 1, 10, 10, 3) 1 1 [0.979]
+Total_time - 336.627 - - - - -
</pre></div>
</div>
</div>
@@ -635,15 +635,15 @@ Total_time -
<span class="k">del</span> <span class="n">debug_module</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
########## 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 79.312 96.587 (1, 6, 10, 10, 1) 2 1 [79.312]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.84 2.241 (1, 6, 10, 10) 1 1 [1.84]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 1.172 (1, 1, 10, 10, 3) 1 1 [0.962]
-Total_time - 82.115 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 88.938 96.988 (1, 6, 10, 10, 1) 2 1 [88.938]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.807 1.971 (1, 6, 10, 10) 1 1 [1.807]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 1.041 (1, 1, 10, 10, 3) 1 1 [0.955]
+Total_time - 91.699 - - - - -
</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 208c01c61..c1eed4b30 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/tmpkk78cada/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpwe3sqvdo/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/tmpkk78cada/images/target contains 8144 images
-/tmp/tmpkk78cada/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/tmpwe3sqvdo/images/target contains 8144 images
+/tmp/tmpwe3sqvdo/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 - 55s - loss: 0.2200 - accuracy: 0.9264 - val_loss: 0.1369 - val_accuracy: 0.9581
+328/328 - 57s - loss: 0.2100 - accuracy: 0.9276 - val_loss: 0.1449 - val_accuracy: 0.9547
Epoch 2/3
-328/328 - 52s - loss: 0.1032 - accuracy: 0.9616 - val_loss: 0.1184 - val_accuracy: 0.9615
+328/328 - 53s - loss: 0.0976 - accuracy: 0.9649 - val_loss: 0.1234 - val_accuracy: 0.9603
Epoch 3/3
-328/328 - 52s - loss: 0.0660 - accuracy: 0.9759 - val_loss: 0.1038 - val_accuracy: 0.9649
+328/328 - 53s - loss: 0.0677 - accuracy: 0.9760 - val_loss: 0.1119 - val_accuracy: 0.9649
-<keras.callbacks.History object at 0x7f4225688510>
+<keras.callbacks.History object at 0x7fa21c557c90>
</pre></div>
</div>
</div>
@@ -819,7 +819,7 @@ Relay model into the MLF intermediate representation. From here, we just need to
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></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 8.196 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 41.494 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 8516ed9e0..e0f7899df 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>06:04.416</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:39.883</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>05:08.196</p></td>
+<td><p>05:41.494</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>00:44.338</p></td>
+<td><p>00:46.039</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>00:08.533</p></td>
+<td><p>00:08.733</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>00:03.346</p></td>
+<td><p>00:03.615</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 bfa7575a4..775c9e980 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>00:42.949</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.229</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>00:31.415</p></td>
+<td><p>00:31.768</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>00:09.945</p></td>
+<td><p>00:09.943</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>00:01.583</p></td>
+<td><p>00:01.510</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_relay/using_external_lib.html b/docs/how_to/work_with_relay/using_external_lib.html
index 48bee4faf..bdae27fee 100644
--- a/docs/how_to/work_with_relay/using_external_lib.html
+++ b/docs/how_to/work_with_relay/using_external_lib.html
@@ -430,7 +430,7 @@ By setting the logging level to DEBUG, the result of Relay graph compilation wil
<span class="n">out_cuda</span> <span class="o">=</span> <span class="n">out</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -854,7 +854,7 @@ To do that, all we need to do is to append the option ” -libs=cudnn” to the
<span class="n">out_cudnn</span> <span class="o">=</span> <span class="n">out</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/work_with_relay/using_pipeline_executor.html b/docs/how_to/work_with_relay/using_pipeline_executor.html
index 08a91449e..d768bd0ea 100644
--- a/docs/how_to/work_with_relay/using_pipeline_executor.html
+++ b/docs/how_to/work_with_relay/using_pipeline_executor.html
@@ -546,7 +546,7 @@ Use CUTLASS BYOC to build the second subgraph module.</p>
<span class="n">pipeline_mod_factory</span> <span class="o">=</span> <span class="n">pipeline_executor_build</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">pipe_config</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
@@ -602,7 +602,7 @@ or synchronously. In the following example, it is synchronous.</p>
<span class="n">out</span> <span class="o">=</span> <a href="../../reference/api/python/graph_executor.html#tvm.contrib.graph_executor.GraphModule.get_output" title="tvm.contrib.graph_executor.GraphModule.get_output" class="sphx-glr-backref-module-tvm-contrib-graph_executor sphx-glr-backref-type-py-method"><span class="n">module1</span><span class="o">.</span><span class="n">get_output</span></a><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <a href="../../refe [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/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. "
</pre></div>
</div>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 17d1544c6..9a347fd24 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 0x7f4188dc1050>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa19017c950>
</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 e279d7f91..449ebb1ab 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>00:04.178</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.402</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,35 +336,35 @@
</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>00:01.901</p></td>
+<td><p>00:02.069</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>00:01.019</p></td>
+<td><p>00:01.014</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>00:00.578</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>00:00.529</p></td>
+<td><p>00:00.556</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>00:00.099</p></td>
+<td><p>00:00.102</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>00:00.041</p></td>
+<td><p>00:00.042</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>
-<td><p>00:00.027</p></td>
+<td><p>00:00.026</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.016</p></td>
+<td><p>00:00.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index f45dcf2c2..4affbdb73 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/tmpav3gf_o6/input0.cc'\nsource_filename = \"/tmp/tmpav3gf_o6/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/tmptlpubt_5/input0.cc'\nsource_filename = \"/tmp/tmptlpubt_5/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/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 38de5b0ec..80734a09d 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/python/driver.html b/docs/reference/api/python/driver.html
index 791e58be5..ebbb00211 100644
--- a/docs/reference/api/python/driver.html
+++ b/docs/reference/api/python/driver.html
@@ -402,8 +402,7 @@ for devices coupled with target information.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
-<li><p><strong>inputs</strong> (<em>Union</em><em>[</em><a class="reference internal" href="te.html#tvm.te.Schedule" title="tvm.te.schedule.Schedule"><em>tvm.te.schedule.Schedule</em></a><em>,</em>) – tvm.tir.PrimFunc, IRModule, Mapping[str, IRModule]]
-The input to be built</p></li>
+<li><p><strong>inputs</strong> (<em>Union</em><em>[</em><a class="reference internal" href="te.html#tvm.te.Schedule" title="tvm.te.schedule.Schedule"><em>tvm.te.schedule.Schedule</em></a><em>, </em><a class="reference internal" href="tir.html#tvm.tir.PrimFunc" title="tvm.tir.PrimFunc"><em>tvm.tir.PrimFunc</em></a><em>, </em><a class="reference internal" href="ir.html#tvm.ir.IRModule" title="tvm.ir.IRModule"><em>IRModule</em></a><em>, </em><em>Mapping</em><em>[</em><a class="reference ext [...]
<li><p><strong>args</strong> (<em>Optional</em><em>[</em><em>List</em><em>[</em><em>Union</em><em>[</em><a class="reference internal" href="tir.html#tvm.tir.Buffer" title="tvm.tir.Buffer"><em>tvm.tir.Buffer</em></a><em>, </em><a class="reference internal" href="te.html#tvm.te.Tensor" title="tvm.te.tensor.Tensor"><em>tensor.Tensor</em></a><em>, </em><a class="reference internal" href="tir.html#tvm.tir.Var" title="tvm.tir.Var"><em>Var</em></a><em>]</em><em>]</em><em>]</em>) – The argument [...]
<li><p><strong>target</strong> (<em>Optional</em><em>[</em><em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><a class="reference internal" href="target.html#tvm.target.Target" title="tvm.target.Target"><em>Target</em></a><em>]</em><em>]</em>) – The target and option of the compilation.</p></li>
<li><p><strong>target_host</strong> (<em>Optional</em><em>[</em><em>Union</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><a class="reference internal" href="target.html#tvm.target.Target" title="tvm.target.Target"><em>Target</em></a><em>]</em><em>]</em>) – Host compilation target, if target is device.
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index d744baab8..4e8bddf80 100644
--- a/docs/reference/api/typedoc/classes/bytestreamreader.html
+++ b/docs/reference/api/typedoc/classes/bytestreamreader.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 2121c9f78..5ca4f0725 100644
--- a/docs/reference/api/typedoc/classes/cachedcallstack.html
+++ b/docs/reference/api/typedoc/classes/cachedcallstack.html
@@ -144,7 +144,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L223">memory.ts:223</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">temp<wbr>Args<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L208">memory.ts:208</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -194,7 +194,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L312">memory.ts:312</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L284">memory.ts:284</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L388">memory.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -300,7 +300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L376">memory.ts:376</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -340,7 +340,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L267">memory.ts:267</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -373,7 +373,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L243">memory.ts:243</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -390,7 +390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L321">memory.ts:321</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -422,7 +422,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L252">memory.ts:252</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -444,7 +444,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L359">memory.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -470,7 +470,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L342">memory.ts:342</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -496,7 +496,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L350">memory.ts:350</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -522,7 +522,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L326">memory.ts:326</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -548,7 +548,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L363">memory.ts:363</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L346">memory.ts:346</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index 3409e3696..7df30742e 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 8be95ba03..19eddef0b 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 51e57acba..aca34bcb7 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/environment.ts#L86">environment.ts:86</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<aside class="tsd-sources">
<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/environment.ts#L70">environment.ts:70</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/environment.ts#L69">environment.ts:69</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/environment.ts#L78">environment.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/environment.ts#L84">environment.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index 6d652fa6b..a2be9cabd 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 49b0f4698..a1f98dae4 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 7a23265de..8ede22063 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 8f003dd77..095df2c51 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index d3df2636a..d6165bb67 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4280d673f/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index cd79e7416..cd9f3b57d 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/fae79bbc3/web/src/runtime.ts#L304">runtime.ts:304</a></li>
... 2127 lines suppressed ...