You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/09/27 11:22:12 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@7a4c10c44a9255ac2fa52ce7e3a83f718d60823f)
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 6d0fe21a2b deploying docs (apache/tvm@7a4c10c44a9255ac2fa52ce7e3a83f718d60823f)
6d0fe21a2b is described below
commit 6d0fe21a2bd003434cd4e0bb58cdb7855a9dd4a7
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Sep 27 11:22:04 2022 +0000
deploying docs (apache/tvm@7a4c10c44a9255ac2fa52ce7e3a83f718d60823f)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 331892 -> 314727 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23825 -> 23008 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2594 +++++++++++++++++---
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 86 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 192 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../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 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 20 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 30 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 17 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 39 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2594 +++++++++++++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 86 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 192 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
.../api/doxygen/namespacemembers_func_m.html | 2 +-
docs/reference/api/doxygen/namespacemembers_m.html | 2 +-
.../doxygen/namespacetvm_1_1tir_1_1transform.html | 23 +-
docs/reference/api/doxygen/search/all_e.js | 2 +-
docs/reference/api/doxygen/search/functions_d.js | 2 +-
docs/reference/api/doxygen/tir_2transform_8h.html | 6 +-
.../api/doxygen/tir_2transform_8h_source.html | 4 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/tir.html | 17 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 273 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
133 files changed, 5568 insertions(+), 1826 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 9ba43750df..44d42e7073 100644
Binary files a/docs/_images/sphx_glr_micro_train_001.png and b/docs/_images/sphx_glr_micro_train_001.png differ
diff --git a/docs/_images/sphx_glr_micro_train_thumb.png b/docs/_images/sphx_glr_micro_train_thumb.png
index d025dae545..979e8de9bd 100644
Binary files a/docs/_images/sphx_glr_micro_train_thumb.png and b/docs/_images/sphx_glr_micro_train_thumb.png differ
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 acb46d030f..d15cf92deb 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.001 seconds)
+ **Total running time of the script:** ( 1 minutes 9.928 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 39abcd3099..96566a3e76 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 942ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 946ms/step
Keras top-1 id: 285, class name: Egyptian cat
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 6d7e54d10e..6fa500286e 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.zipfc9dc6c1-d731-4bae-8015-b5cf3e9e8b9b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipb02da895-219d-4f55-a72e-696c202702f9 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index 93f3fffced..dd9cf4b27e 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ 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, 46.9MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 34.2MB/s]
43%|####2 | 17.7M/41.5M [00:00<00:00, 33.8MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 30.4MB/s]
61%|###### | 25.3M/41.5M [00:00<00:00, 29.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.3MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 46.7MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
16%|#6 | 6.76M/41.5M [00:00<00:00, 70.9MB/s]
33%|###2 | 13.5M/41.5M [00:00<00:00, 56.2MB/s]
48%|####8 | 19.9M/41.5M [00:00<00:00, 60.6MB/s]
62%|######2 | 25.9M/41.5M [00:00<00:00, 47.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 50.5MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 39.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 47.0MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 4120b6da97..57a9ac4321 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]
1%| | 440k/44.7M [00:00<00:10, 4.34MB/s]
3%|2 | 1.12M/44.7M [00:00<00:07, 5.97MB/s]
4%|4 | 1.95M/44.7M [00:00<00:06, 7.17MB/s]
7%|6 | 2.98M/44.7M [00:00<00:05, 8.61MB/s]
10%|9 | 4.29M/44.7M [00:00<00:04, 10.3MB/s]
13%|#3 | 5.98M/44.7M [00:00<00:03, 12.8MB/s]
18%|#7 | 8.00M/44.7M [00:00<00:02, 15.5MB/s]
24%|##3 | 10.6M/44.7M [00:00<00:01, 19.2MB/s]
31%|### | 13.8M/44.7M [00:00<00:01, 23.7MB/s]
40%|#### | 17.9M/44.7M [00:01<00:00, 29.5MB/s]
51%|#####1 | 22.9M/44.7M [00:01<00:00, 36.5MB/s]
65%|######5 | 29.1M/44.7M [00:01<00:00, 45.0MB/s]
81%|######## | 36.1M/44.7M [00:01<00:00, 53.4MB/s]
97%|#########6| 43.3M/44.7M [00:01<00:00, 60.1MB/s]
100%|##########| 44.7M/44.7M [00:01<00:00, 32.7MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
11%|#1 | 4.95M/44.7M [00:00<00:00, 51.9MB/s]
22%|##2 | 9.91M/44.7M [00:00<00:00, 51.3MB/s]
59%|#####9 | 26.4M/44.7M [00:00<00:00, 107MB/s]
97%|#########7| 43.4M/44.7M [00:00<00:00, 135MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 115MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index ac3f09666f..4b8803deb1 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.510 seconds)
+ **Total running time of the script:** ( 1 minutes 11.567 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index 9c467cea2d..d08742faea 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
=================
-**05:38.701** total execution time for **how_to_compile_models** files:
+**05:35.183** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:12.001 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.567 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.510 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.928 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.326 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:44.462 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:30.283 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:30.865 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.400 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:27.709 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.603 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.167 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:24.732 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.489 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.113 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:15.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.164 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.911 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.476 | 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 bf8404635a..5a2e512bec 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
@@ -434,7 +434,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9066 15.8665 16.2268 15.6885 0.1617
+ 16.0986 15.6962 19.4010 15.5811 1.1109
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 29acd23798..f64503c178 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]
6%|5 | 9.45M/170M [00:00<00:01, 99.1MB/s]
17%|#6 | 28.7M/170M [00:00<00:00, 159MB/s]
33%|###3 | 56.1M/170M [00:00<00:00, 218MB/s]
49%|####9 | 84.0M/170M [00:00<00:00, 247MB/s]
68%|######7 | 115M/170M [00:00<00:00, 277MB/s]
84%|########3 | 142M/170M [00:00<00:00, 251MB/s]
98%|#########7| 166M/170M [00:00<00:00, 241MB/s]
100%|##########| 170M/170M [00:00<00:00, 234MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
11%|# | 17.9M/170M [00:00<00:00, 187MB/s]
26%|##6 | 44.2M/170M [00:00<00:00, 240MB/s]
42%|####1 | 71.2M/170M [00:00<00:00, 259MB/s]
57%|#####7 | 97.6M/170M [00:00<00:00, 266MB/s]
73%|#######2 | 124M/170M [00:00<00:00, 270MB/s]
89%|########8 | 150M/170M [00:00<00:00, 272MB/s]
100%|##########| 170M/170M [00:00<00:00, 264MB/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').
@@ -288,7 +288,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 7.006 seconds)
+ **Total running time of the script:** ( 3 minutes 4.456 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 ea533bc743..33c408e5f5 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]
83%|########3 | 11.3M/13.6M [00:00<00:00, 118MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 130MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
30%|### | 4.07M/13.6M [00:00<00:00, 42.6MB/s]
63%|######2 | 8.52M/13.6M [00:00<00:00, 45.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 62.2MB/s]
@@ -405,7 +405,7 @@ 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)
- 90.3860 90.2612 93.0289 90.0348 0.4464
+ 90.2022 90.1283 94.2429 89.8640 0.4784
@@ -454,7 +454,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.466 seconds)
+ **Total running time of the script:** ( 1 minutes 17.489 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 2508e79bcb..e2afe6f39e 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
@@ -432,7 +432,7 @@ 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)
- 120.3369 120.1555 122.8037 119.4390 0.5698
+ 119.6808 119.7133 123.9559 117.4201 0.7975
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 0.036 seconds)
+ **Total running time of the script:** ( 1 minutes 53.873 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 7819697246..119c9e2c0c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.954 seconds)
+ **Total running time of the script:** ( 1 minutes 30.969 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 a5fdb07568..0e42fd83df 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]
5%|4 | 6131/132723 [00:00<00:02, 61300.27KB/s]
10%|# | 13666/132723 [00:00<00:01, 69552.71KB/s]
16%|#5 | 20622/132723 [00:00<00:02, 47843.65KB/s]
21%|##1 | 28029/132723 [00:00<00:01, 55963.72KB/s]
27%|##6 | 35428/132723 [00:00<00:01, 61490.62KB/s]
32%|###2 | 42868/132723 [00:00<00:01, 65421.43KB/s]
38%|###7 | 50334/132723 [00:00<00:01, 68222.02KB/s]
43%|####3 | 57682/132723 [00:00<00:01, 69809.60KB/s]
49%|####8 | 64849/132723 [00:01<00:00, 69673.64KB/s]
54%|#####4 | 72233/132723 [00:01<00:00, 70918.02KB/s]
60%|###### | 79678/132723 [00:01<00:00, 71972.54KB/s]
66%|######5 | 87179/132723 [00:01<00:00, 72880.21KB/s]
71%|#######1 | 94708/132723 [00:01<00:00, 73599.84KB/s]
77%|#######7 | 102257/132723 [00:01<00:00, 74155.25KB/s]
83%|########2 | 109842/132723 [00:01<00:00, 74661.84KB/s]
88%|########8
| 117431/132723 [00:01<00:00, 74996.51KB/s]
94%|#########4| 125045/132723 [00:01<00:00, 75337.36KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75633.38KB/s]
100%|##########| 132723/132723 [00:01<00:00, 69683.67KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6036/132723 [00:00<00:02, 60351.42KB/s]
10%|# | 13557/132723 [00:00<00:01, 67968.73KB/s]
16%|#5 | 20904/132723 [00:00<00:01, 70454.30KB/s]
21%|##1 | 28408/132723 [00:00<00:01, 72251.59KB/s]
27%|##6 | 35814/132723 [00:00<00:01, 72898.32KB/s]
33%|###2 | 43352/132723 [00:00<00:01, 73737.68KB/s]
38%|###8 | 50913/132723 [00:00<00:01, 74345.18KB/s]
44%|####3 | 58348/132723 [00:00<00:01, 73729.56KB/s]
50%|####9 | 65891/132723 [00:00<00:00, 74256.67KB/s]
55%|#####5 | 73444/132723 [00:01<00:00, 74645.94KB/s]
61%|######1 | 81082/132723 [00:01<00:00, 75173.31KB/s]
67%|######6 | 88601/132723 [00:01<00:00, 74866.91KB/s]
72%|#######2 | 96152/132723 [00:01<00:00, 75058.67KB/s]
78%|#######8 | 103763/132723 [00:01<00:00, 75373.25KB/s]
84%|########4 | 111493/132723 [00:01<00:00, 75947.88KB/s]
90%|########9
| 119225/132723 [00:01<00:00, 76359.38KB/s]
96%|#########5| 126984/132723 [00:01<00:00, 76727.11KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74541.48KB/s]
@@ -234,7 +234,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 48.350 seconds)
+ **Total running time of the script:** ( 2 minutes 46.443 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 36dac04dca..6d0f9ff6d0 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
=================
-**12:12.344** total execution time for **how_to_deploy_models** files:
+**11:56.099** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:07.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:04.456 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:48.350 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:46.443 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:00.036 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.873 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:32.954 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:30.969 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:19.466 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:17.489 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.200 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.820 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.900 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:24.270 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.426 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.773 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index d8cd94349f..cee737ff53 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
@@ -472,7 +472,7 @@ 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.zip69f95595-c52c-4684-b263-83c405e4a374 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa98ba8ef-1d98-45bd-bcb4-3fb39158bd78 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index bc91f97caf..d09eab6d3d 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
=================
-**00:44.734** total execution time for **how_to_extend_tvm** files:
+**00:44.639** 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``) | 00:41.403 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:41.304 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.332 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.340 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.991 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.986 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index f40dac98d0..e610198d69 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: 6858us [6858us] (46.21%; 46.21%)
- FoldScaleAxis: 7982us [6us] (53.79%; 53.79%)
- FoldConstant: 7976us [1646us] (53.75%; 99.93%)
- InferType: 6329us [6329us] (42.65%; 79.36%)
+ InferType: 6689us [6689us] (46.04%; 46.04%)
+ FoldScaleAxis: 7840us [5us] (53.96%; 53.96%)
+ FoldConstant: 7835us [1639us] (53.93%; 99.94%)
+ InferType: 6196us [6196us] (42.65%; 79.08%)
@@ -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: 6295us [6295us] (44.48%; 44.48%)
- FoldScaleAxis: 7859us [5us] (55.52%; 55.52%)
- FoldConstant: 7854us [1622us] (55.49%; 99.94%)
- InferType: 6232us [6232us] (44.03%; 79.35%)
+ InferType: 6249us [6249us] (44.48%; 44.48%)
+ FoldScaleAxis: 7801us [4us] (55.52%; 55.52%)
+ FoldConstant: 7797us [1632us] (55.49%; 99.95%)
+ InferType: 6165us [6165us] (43.88%; 79.07%)
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 9db3f1f6ce..62db2be6b4 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: 35.307552 ms
+ Convolution: 40.713310 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 d9e5b104b4..4a85cc3c3b 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: 13.351926 ms
+ conv2d with tensor core: 9.861722 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 2e9befd70a..cae4425fa2 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: 0.018546
- Baseline: 3.254144
+ Numpy running time: 0.017874
+ Baseline: 3.452391
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.303355
+ Opt1: 0.293947
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.336773
+ Opt2: 0.332670
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115589
+ Opt3: 0.114966
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109823
+ Opt4: 0.109266
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111114
+ Opt5: 0.111201
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146586
+ Opt6: 0.145125
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 3a40e8b272..4a8d32d6c5 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
=================
-**00:34.197** total execution time for **how_to_optimize_operators** files:
+**00:34.410** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.821 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.077 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.354 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.272 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.061 | 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 e86aab6ea5..c3a3f49d9e 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
=================
-**06:53.002** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:39.802** 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``) | 03:40.678 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:29.614 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:29.211 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:29.247 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:59.377 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:58.886 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:22.883 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:21.208 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.488 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:10.592 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:10.365 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:10.255 | 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 c3c649ba96..2a9d089f23 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
@@ -240,205 +240,1156 @@ 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" = 32;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), 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" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 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
- for (rc.outer.outer: int32, 0, 8) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*3136)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*576)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + 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 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + 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 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1560)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2128), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2240), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2352), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2464), 9)*7)) + cse_var_3) + 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 + 2576)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2576), 9)*7)) + cse_var_3) + 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 + 2688)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2688), 9)*7)) + cse_var_3) + 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 + 2800)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2800), 9)*7)) + cse_var_3) + 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 + 2912)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2912), 9)*7)) + cse_var_3) + 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 + 3024)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2344)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3136), 9)*7)) + cse_var_3) + 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 + 3248)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3248), 9)*7)) + cse_var_3) + 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 + 3360)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3360), 9)*7)) + cse_var_3) + 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 + 3472)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3472), 9)*7)) + cse_var_3) + 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 + 3584)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3584), 9)*7)) + cse_var_3) + 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 + 3696)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3696), 9)*7)) + cse_var_3) + 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 + 3808)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3808), 9)*7)) + cse_var_3) + 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 + 3920)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3920), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 48), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 672), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1008), 192)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1232), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1456), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1680), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 48), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1792), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1904), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2016), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2128), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2240), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 192)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2464), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2576), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2800), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2912), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3024), 192)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 48)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*24)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod((threadIdx.x_1*24), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
}
- for (rc.outer.inner: int32, 0, 32) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
}
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 18)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 19)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 20)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 350)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 413)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 422)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 431)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 494)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 503)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 655)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 655)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 656)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 660)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 661)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 662)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 663)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 660)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 661)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 662)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 663)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 664)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 660)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 661)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 662)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 663)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 664)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 665)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 669)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 670)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 671)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 672)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 669)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 670)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 671)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 672)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 673)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 669)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 670)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 671)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 672)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 673)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 674)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 732)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 733)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 734)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 732)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 733)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 734)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 736)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 732)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 733)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 734)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 736)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 737)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 741)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 742)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 743)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 744)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 741)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 742)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 743)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 744)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 745)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 741)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 742)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 743)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 744)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 745)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 746)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 750)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 751)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 752)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 753)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 750)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 751)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 752)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 753)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 754)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 750)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 751)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 752)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 753)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 754)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 755)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 813)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 814)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 815)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 816)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 813)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 814)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 815)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 816)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 817)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 813)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 814)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 815)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 816)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 817)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 818)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 907)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 907)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 908)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 912)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 913)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 914)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 915)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 912)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 913)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 914)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 915)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 916)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 912)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 913)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 914)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 915)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 916)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 917)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 975)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 976)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 977)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 978)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 975)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 976)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 977)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 978)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 979)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 975)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 976)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 977)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 978)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 979)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 984)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 985)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 986)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 987)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 984)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 985)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 986)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 987)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 988)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 984)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 985)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 986)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 987)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 988)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 989)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 993)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 994)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 995)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 996)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 993)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 994)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 995)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 996)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 997)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 993)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 994)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 995)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 996)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 997)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 998)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1053)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1056)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1057)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1058)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1059)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1056)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1057)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1058)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1059)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1060)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1056)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1057)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1058)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1059)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1060)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1061)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1062)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1065)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1066)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1067)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1068)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1065)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1066)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1067)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1068)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1069)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1065)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1066)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1067)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1068)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1069)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1070)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1079)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1156)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1157)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1158)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1156)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1157)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1158)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1159)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1156)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1157)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1158)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1159)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1160)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1219)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1220)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1221)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1219)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1220)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1221)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1222)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1219)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1220)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1221)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1222)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1223)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1224)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1228)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1229)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1230)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1228)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1229)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1230)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1231)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1228)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1229)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1230)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1231)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1232)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1233)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1237)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1238)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1239)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1237)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1238)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1239)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1240)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1237)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1238)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1239)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1240)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1241)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- }
+ compute[((blockIdx.x*1568) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
@@ -492,7 +1443,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.216 ms
+ Execution time of this operator: 0.217 ms
@@ -542,35 +1493,35 @@ 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=1)
- 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_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
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=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=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=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=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+ 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=7)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- 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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_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=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
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=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_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=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -589,14 +1540,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ 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=224)
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=1)
+ 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=24)
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=112)
+ 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=224)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -614,10 +1565,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[3072];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -625,125 +1576,1120 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1560)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2128) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2240) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2464) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2576)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2576) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2688)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2688) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2800)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2800) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2912)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2912) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3024)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2344)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3248)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3248) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3360)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3360) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3472)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3472) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3584)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3584) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3696)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3696) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3808)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3808) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1680) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1792) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1904) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2016) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2128) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2240) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2464) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2576) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2800) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2912) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3024) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 432)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[(((int)threadIdx.x) * 24)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && (((((int)threadIdx.x) * 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 1)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 2)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 3)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 4)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 5)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 6)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 7)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 8)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 12)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 13)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 14)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 15)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 16)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 17)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 18)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 19)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 20)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 21)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 22)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 23)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 350)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 413)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 422)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 431)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 494)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 503)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 655)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 655)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 656)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 660)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 661)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 662)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 663)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 660)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 661)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 662)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 663)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 664)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 660)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 661)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 662)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 663)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 664)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 665)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 666)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 669)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 670)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 671)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 672)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 669)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 670)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 671)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 672)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 673)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 669)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 670)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 671)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 672)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 673)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 674)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 729)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 732)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 733)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 734)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 735)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 732)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 733)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 734)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 735)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 736)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 732)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 733)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 734)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 735)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 736)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 737)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 738)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 741)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 742)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 743)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 744)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 741)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 742)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 743)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 744)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 745)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 741)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 742)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 743)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 744)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 745)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 746)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 747)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 750)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 751)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 752)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 753)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 750)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 751)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 752)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 753)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 754)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 750)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 751)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 752)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 753)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 754)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 755)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 810)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 813)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 814)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 815)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 816)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 813)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 814)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 815)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 816)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 817)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 813)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 814)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 815)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 816)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 817)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 818)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 907)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 907)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 908)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 912)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 913)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 914)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 915)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 912)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 913)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 914)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 915)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 916)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 912)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 913)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 914)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 915)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 916)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 917)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 975)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 976)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 977)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 978)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 975)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 976)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 977)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 978)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 979)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 975)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 976)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 977)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 978)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 979)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 980)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 981)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 984)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 985)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 986)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 987)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 984)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 985)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 986)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 987)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 988)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 984)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 985)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 986)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 987)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 988)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 989)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 990)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 993)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 994)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 995)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 996)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 993)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 994)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 995)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 996)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 997)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 993)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 994)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 995)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 996)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 997)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 998)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1053)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1056)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1057)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1058)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1059)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1056)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1057)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1058)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1059)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1060)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1056)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1057)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1058)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1059)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1060)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1061)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1062)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1065)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1066)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1067)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1068)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1065)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1066)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1067)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1068)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1069)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1065)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1066)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1067)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1068)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1069)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1070)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1079)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1156)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1157)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1158)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1156)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1157)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1158)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1159)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1156)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1157)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1158)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1159)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1160)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1219)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1220)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1221)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1219)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1220)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1221)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1222)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1219)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1220)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1221)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1222)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1223)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1224)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1228)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1229)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1230)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1228)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1229)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1230)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1231)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1228)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1229)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1230)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1231)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1232)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1233)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1237)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1238)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1239)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1237)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1238)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1239)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1240)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1237)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1238)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1239)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1240)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1241)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- }
+ compute[((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
@@ -804,7 +2750,7 @@ 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 40.678 seconds)
+ **Total running time of the script:** ( 3 minutes 29.614 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py:
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
index 4e5d721aae..b33288d74a 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
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2542 8.2539 8.2554 8.2532 0.0009
+ 8.1955 8.2007 8.2013 8.1845 0.0078
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 6577a0dbfa..97551a91e1 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
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 746.2183 745.7884 747.5492 745.3171 0.9606
+ 755.1963 754.5660 756.6738 754.3492 1.0485
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 29.211 seconds)
+ **Total running time of the script:** ( 1 minutes 29.247 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 3a9c2edd44..ae670ccf3b 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
@@ -397,30 +397,80 @@ 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 = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 2) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [256], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 2) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048)) + (i.inner*256))
+ let cse_var_17: int32 = (cse_var_19 + 9)
+ let cse_var_16: int32 = (cse_var_19 + 8)
+ let cse_var_15: int32 = (cse_var_19 + 7)
+ let cse_var_14: int32 = (cse_var_19 + 6)
+ let cse_var_13: int32 = (cse_var_19 + 5)
+ let cse_var_12: int32 = (cse_var_19 + 4)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 2)
+ let cse_var_9: int32 = (cse_var_19 + 15)
+ let cse_var_8: int32 = (cse_var_19 + 14)
+ let cse_var_7: int32 = (cse_var_19 + 13)
+ let cse_var_6: int32 = (cse_var_19 + 12)
+ let cse_var_5: int32 = (cse_var_19 + 11)
+ let cse_var_4: int32 = (cse_var_19 + 10)
+ let cse_var_3: int32 = (cse_var_19 + 1)
+ {
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -476,7 +526,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.189 ms
+ Execution time of this operator: 1.838 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 403f5d29c9..ecb47706e5 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:45.102** total execution time for **how_to_tune_with_autotvm** files:
+**00:30.402** 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``) | 00:45.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:30.367 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 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_cuda.py` (``tune_relay_cuda.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 76a8e7e5cd..4f02d780b5 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
@@ -277,9 +277,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 26.51/26.51 result: MeasureResult(costs=(0.0087316115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.707612037658691, timestamp=1664264288.1242013) [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3500701
- No: 2 GFLOPS: 269.46/269.46 result: MeasureResult(costs=(0.000859136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.621802568435669, timestamp=1664264288.811587) [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5861275
- No: 3 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 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
@@ -401,8 +399,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7906761
- No: 4 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,593877
+ No: 2 GFLOPS: 97.62/97.62 result: MeasureResult(costs=(0.002371547847826087,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1653003692626953, timestamp=1664273482.081091) [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7551857
+ No: 3 GFLOPS: 40.70/97.62 result: MeasureResult(costs=(0.005688332444444445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5143184661865234, timestamp=1664273483.8374388) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8923280
+ No: 4 GFLOPS: 0.00/97.62 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
@@ -524,8 +524,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9432430
- No: 5 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8412681
+ No: 5 GFLOPS: 0.00/97.62 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
@@ -647,8 +647,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9391826
- No: 6 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6672635
+ No: 6 GFLOPS: 0.00/97.62 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
@@ -770,10 +770,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1370925
- No: 7 GFLOPS: 211.65/269.46 result: MeasureResult(costs=(0.0010937779387755102,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4072532653808594, timestamp=1664264294.042101) [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2559794
- No: 8 GFLOPS: 30.92/269.46 result: MeasureResult(costs=(0.007486210357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4876489639282227, timestamp=1664264294.7134411) [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330604
- No: 9 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6613456
+ No: 7 GFLOPS: 35.33/97.62 result: MeasureResult(costs=(0.006553338411764705,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4227442741394043, timestamp=1664273487.6779063) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5887424
+ No: 8 GFLOPS: 0.00/97.62 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
@@ -895,9 +894,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934894
- No: 10 GFLOPS: 5.93/269.46 result: MeasureResult(costs=(0.039066184749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.5282135009765625, timestamp=1664264302.4238741) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8341500
- No: 11 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3663876
+ No: 9 GFLOPS: 5.20/97.62 result: MeasureResult(costs=(0.0445004805,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2675786018371582, timestamp=1664273489.5801508) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,605542
+ No: 10 GFLOPS: 0.00/97.62 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
@@ -1019,8 +1018,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7884556
- No: 12 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10025409
+ No: 11 GFLOPS: 0.00/97.62 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
@@ -1142,8 +1141,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7769621
- No: 13 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7341565
+ No: 12 GFLOPS: 78.43/97.62 result: MeasureResult(costs=(0.0029518690545454547,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7027909755706787, timestamp=1664273490.5161994) [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4295417
+ No: 13 GFLOPS: 0.00/97.62 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
@@ -1265,8 +1265,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3504569
- No: 14 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9868006
+ No: 14 GFLOPS: 0.00/97.62 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
@@ -1388,8 +1388,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 1, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6923396
- No: 15 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1461908
+ No: 15 GFLOPS: 0.00/97.62 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
@@ -1511,8 +1511,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3431971
- No: 16 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8104269
+ No: 16 GFLOPS: 0.00/97.62 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
@@ -1634,8 +1634,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2737510
- No: 17 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6575292
+ No: 17 GFLOPS: 23.68/97.62 result: MeasureResult(costs=(0.009774371,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2793161869049072, timestamp=1664273492.161263) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6790136
+ No: 18 GFLOPS: 236.64/236.64 result: MeasureResult(costs=(0.000978286187878788,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3463761806488037, timestamp=1664273493.0877633) [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,405495
+ No: 19 GFLOPS: 0.00/236.64 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
@@ -1757,8 +1759,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8053816
- No: 18 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2044362
+ No: 20 GFLOPS: 0.00/236.64 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
@@ -1880,131 +1882,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5277149
- No: 19 GFLOPS: 0.00/269.46 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 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)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- 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
-
- Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1220402
- No: 20 GFLOPS: 60.89/269.46 result: MeasureResult(costs=(0.003802074,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.675763130187988, timestamp=1664264313.508275) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8062186
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3886463
@@ -2059,9 +1937,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5861275
+ [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,405495
Finish loading 20 records
- Time cost of this operator: 0.001235
+ Time cost of this operator: 0.001389
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 b0867e1f2b..31e1c34ec7 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
@@ -327,10 +327,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.3 98.702 (1, 2, 10, 10, 3) 2 1 [311.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.13 0.992 (1, 6, 10, 10) 1 1 [3.13]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.305 (1, 1, 10, 10, 3) 1 1 [0.963]
- Total_time - 315.393 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.1 98.743 (1, 2, 10, 10, 3) 2 1 [316.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.049 0.952 (1, 6, 10, 10) 1 1 [3.049]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.304 (1, 1, 10, 10, 3) 1 1 [0.974]
+ Total_time - 320.123 - - - - -
@@ -394,10 +394,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 97.364 (1, 6, 10, 10, 1) 2 1 [100.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.703 (1, 6, 10, 10) 1 1 [1.75]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.933 (1, 1, 10, 10, 3) 1 1 [0.96]
- Total_time - 102.81 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.5 97.462 (1, 6, 10, 10, 1) 2 1 [102.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.822 1.733 (1, 6, 10, 10) 1 1 [1.822]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.847 0.805 (1, 3, 10, 10, 1) 1 1 [0.847]
+ Total_time - 105.169 - - - - -
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 48702c3780..cd6c2e8e22 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/tmpu3e79fd5/images/random'
+ '/tmp/tmpffx_fugf/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [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], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpu3e79fd5/images/target contains 8144 images
- /tmp/tmpu3e79fd5/images/random contains 5000 images
+ /tmp/tmpffx_fugf/images/target contains 8144 images
+ /tmp/tmpffx_fugf/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 46s - loss: 0.2115 - accuracy: 0.9254 - val_loss: 0.1110 - val_accuracy: 0.9607 - 46s/epoch - 141ms/step
+ 328/328 - 47s - loss: 0.2181 - accuracy: 0.9239 - val_loss: 0.1244 - val_accuracy: 0.9653 - 47s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0983 - accuracy: 0.9639 - val_loss: 0.0959 - val_accuracy: 0.9664 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.1013 - accuracy: 0.9617 - val_loss: 0.1932 - val_accuracy: 0.9400 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0638 - accuracy: 0.9761 - val_loss: 0.1963 - val_accuracy: 0.9396 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0657 - accuracy: 0.9757 - val_loss: 0.1148 - val_accuracy: 0.9619 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7f8d38fc1510>
+ <keras.callbacks.History object at 0x7f87df6f59d0>
@@ -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:** ( 4 minutes 35.116 seconds)
+ **Total running time of the script:** ( 4 minutes 38.337 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 d3019d017a..7e5419f113 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
=================
-**05:43.748** total execution time for **how_to_work_with_microtvm** files:
+**05:47.013** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:35.116 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:38.337 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:55.236 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:55.346 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.352 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.245 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:04.083 | 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 e0828eb38d..aefcabd076 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
=================
-**00:43.299** total execution time for **how_to_work_with_relay** files:
+**00:43.084** 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``) | 00:31.740 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.757 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.053 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.870 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.450 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index e1a5abe67d..3f867b544e 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 0x7f8d35f56950>
+ <function my_cuda_math_rule at 0x7f87e5cfc830>
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 64036b6ce0..f149ab69f1 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**00:07.854** total execution time for **how_to_work_with_schedules** files:
+**00:07.751** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.589 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.425 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.013 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.547 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.569 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.526 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.551 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.113 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.039 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.040 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 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 73029b0e87..63461ab167 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/tmp3q6u3ki5/input0.cc'\nsource_filename = \"/tmp/tmp3q6u3ki5/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/tmp48ppcfty/input0.cc'\nsource_filename = \"/tmp/tmp48ppcfty/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 ed89fc2818..9149e13e6c 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
=================
-**00:25.587** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:24.777** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.580 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:24.771 | 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/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index af36b75981..162c0a2c86 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 26.70s!
+ resnet18_v1 inference graph built in 26.32s!
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 663230acea..b7864920ba 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 18.62s!
+ yolov3-tiny inference graph built in 18.38s!
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 3acc7035f2..8eca331788 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
=================
-**01:37.849** total execution time for **topic_vta_tutorials_frontend** files:
+**01:37.609** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.262 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.017 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:46.587 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:46.592 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 76a9eff221..d290867c73 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
=================
-**00:03.025** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.108** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.618 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.684 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.406 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.424 | 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 e55f31cc45..f11bb71e20 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
=================
-**00:00.731** total execution time for **topic_vta_tutorials** files:
+**00:00.795** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.384 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.424 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.347 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.371 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 1886f46b38..8cda067f8e 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,6 +203,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+
+
@@ -326,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.816 ms
+ Execution time of this operator: 93.224 ms
@@ -444,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.828 seconds)
+ **Total running time of the script:** ( 1 minutes 2.702 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 491abe90da..f51499b93e 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: 2.79/2.79 result: MeasureResult(costs=(0.096159805,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6840178966522217, timestamp=1664262981.3861105) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
- No: 2 GFLOPS: 2.08/2.79 result: MeasureResult(costs=(0.1292843458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2713046073913574, timestamp=1664262983.664887) [('tile_y', [-1, 128]), ('tile_x', [-1, 4])],None,27
- No: 3 GFLOPS: 10.55/10.55 result: MeasureResult(costs=(0.025443878000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5890531539916992, timestamp=1664262985.1424325) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 4 GFLOPS: 8.51/10.55 result: MeasureResult(costs=(0.0315400358,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.831183671951294, timestamp=1664262986.7137284) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
- No: 5 GFLOPS: 10.28/10.55 result: MeasureResult(costs=(0.026124543,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5663766860961914, timestamp=1664262988.313322) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
- No: 6 GFLOPS: 2.05/10.55 result: MeasureResult(costs=(0.13090462500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.229414463043213, timestamp=1664262990.5744553) [('tile_y', [-1, 4]), ('tile_x', [-1, 1])],None,2
- No: 7 GFLOPS: 2.09/10.55 result: MeasureResult(costs=(0.1284661566,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.184475898742676, timestamp=1664262992.7937398) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 8 GFLOPS: 0.51/10.55 result: MeasureResult(costs=(0.5264441124,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.610341310501099, timestamp=1664263001.428544) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
- No: 9 GFLOPS: 10.78/10.78 result: MeasureResult(costs=(0.0248948048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5744311809539795, timestamp=1664263002.1178017) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
- No: 10 GFLOPS: 2.00/10.78 result: MeasureResult(costs=(0.13407361739999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.276829481124878, timestamp=1664263004.429098) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
+ No: 1 GFLOPS: 1.90/1.90 result: MeasureResult(costs=(0.1410182802,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4015309810638428, timestamp=1664272209.7391603) [('tile_y', [-1, 1]), ('tile_x', [-1, 8])],None,30
+ No: 2 GFLOPS: 8.77/8.77 result: MeasureResult(costs=(0.0306142488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6932034492492676, timestamp=1664272211.3172941) [('tile_y', [-1, 512]), ('tile_x', [-1, 128])],None,79
+ No: 3 GFLOPS: 3.08/8.77 result: MeasureResult(costs=(0.08717574560000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.547947883605957, timestamp=1664272212.8774598) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 4 GFLOPS: 3.93/8.77 result: MeasureResult(costs=(0.0682275626,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.235006332397461, timestamp=1664272215.0477853) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+ No: 5 GFLOPS: 10.68/10.68 result: MeasureResult(costs=(0.0251460798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5613391399383545, timestamp=1664272215.7629805) [('tile_y', [-1, 2]), ('tile_x', [-1, 256])],None,81
+ No: 6 GFLOPS: 11.01/11.01 result: MeasureResult(costs=(0.024379073600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5853981971740723, timestamp=1664272216.3247697) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
+ No: 7 GFLOPS: 11.69/11.69 result: MeasureResult(costs=(0.0229641028,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5406255722045898, timestamp=1664272217.7683709) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+ No: 8 GFLOPS: 2.77/11.69 result: MeasureResult(costs=(0.0968329,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7436046600341797, timestamp=1664272219.5336573) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 9 GFLOPS: 10.26/11.69 result: MeasureResult(costs=(0.0261749224,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6147301197052002, timestamp=1664272220.2613976) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
+ No: 10 GFLOPS: 11.40/11.69 result: MeasureResult(costs=(0.0235371542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.49225568771362305, timestamp=1664272220.8040233) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 435536430f..8df8fba5af 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 513.5714736600005, 'median': 514.0005617999975, 'std': 2.4411642308100787}
+ {'mean': 512.2266732599974, 'median': 511.84938844999124, 'std': 2.0156171937905514}
@@ -554,30 +554,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.83/ 23.04 GFLOPS | Progress: (4/20) | 10.06 s
[Task 1/25] Current/Best: 8.19/ 23.04 GFLOPS | Progress: (8/20) | 16.06 s
[Task 1/25] Current/Best: 9.17/ 23.04 GFLOPS | Progress: (12/20) | 18.84 s
[Task 1/25] Current/Best: 18.46/ 23.04 GFLOPS | Progress: (16/20) | 20.54 s
[Task 1/25] Current/Best: 11.22/ 23.69 GFLOPS | Progress: (20/20) | 23.09 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 13.74/ 13.74 GFLOPS | Progress: (4/20) | 3.58 s
[Task 2/25] Current/Best: 13.71/ 21.93 GFLOPS | Progress: (8/20) | 4.63 s
[Task 2/25] Current/Best: 15.34/ 21.93 GFLOPS | Progress: (12/20) | 6.47 s
[Task 2/25] Current/Best: 9.50/ 21.93 GFLOPS | Progress: (16/20) | 8.11 s
[Task 2/25] Current/Best: 13.05/ 21.93 GFLOPS | Progress: (20/20) | 9.92 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 7.03/ 17.63 GFLOPS | Progress: (4/20) | 3.73 s
[Task 3/25] Current/Best: 11.14/ 17.63 GFLOPS | Progress: (8/20) | 5.89 s
[Task 3/25] Current/Best: 12.36/ 17.71 GFLOPS | Progress: (12/20) | 7.61 s
[Task 3/25] Current/Best: 3.18/ 19.93 GFLOPS | Progress: (16/20) | 10.08 s
[Task 3/25] Current/Best: 12.22/ 20.53 GFLOPS | Progress: (20/20) | 11.86 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.21/ 17.62 GFLOPS | Progress: (4/20) | 3.99 s
[Task 4/25] Current/Best: 15.01/ 17.62 GFLOPS | Progress: (8/20) | 5.51 s
[Task 4/25] Current/Best: 9.77/ 17.62 GFLOPS | Progress: (12/20) | 7.85 s
[Task 4/25] Current/Best: 8.60/ 19.48 GFLOPS | Progress: (16/20) | 9.84 s
[Task 4/25] Current/Best: 14.06/ 19.48 GFLOPS | Progress: (20/20) | 11.76 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 6.04/ 17.22 GFLOPS | Progress: (4/20) | 3.79 s
[Task 5/25] Current/Best: 22.76/ 22.76 GFLOPS | Progress: (8/20) | 5.78 s
[Task 5/25] Current/Best: 15.22/ 22.76 GFLOPS | Progress: (12/20) | 7.18 s
[Task 5/25] Current/Best: 18.48/ 22.76 GFLOPS | Progress: (16/20) | 9.21 s
[Task 5/25] Current/Best: 13.49/ 22.76 GFLOPS | Progress: (20/20) | 10.91 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.44/ 13.44 GFLOPS | Progress: (4/20) | 4.53 s
[Task 6/25] Current/Best: 17.83/ 17.83 GFLOPS | Progress: (8/20) | 6.66 s
[Task 6/25] Current/Best: 5.12/ 18.25 GFLOPS | Progress: (12/20) | 9.08 s
[Task 6/25] Current/Best: 7.99/ 20.35 GFLOPS | Progress: (16/20) | 10.93 s
[Task 6/25] Current/Best: 17.92/ 20.35 GFLOPS | Progress: (20/20) | 13.28 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.79/ 22.04 GFLOPS | Progress: (4/20) | 3.85 s
[Task 7/25] Current/Best: 17.82/ 22.04 GFLOPS | Progress: (8/20) | 7.07 s
[Task 7/25] Current/Best: 17.13/ 22.04 GFLOPS | Progress: (12/20) | 8.92 s
[Task 7/25] Current/Best: 15.49/ 22.04 GFLOPS | Progress: (16/20) | 11.58 s
[Task 7/25] Current/Best: 12.48/ 22.04 GFLOPS | Progress: (20/20) | 14.88 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 14.23/ 14.87 GFLOPS | Progress: (4/20) | 8.15 s
[Task 8/25] Current/Best: 10.84/ 19.91 GFLOPS | Progress: (8/20) | 10.20 s
[Task 8/25] Current/Best: 13.29/ 19.91 GFLOPS | Progress: (12/20) | 15.10 s
[Task 8/25] Current/Best: 9.31/ 19.91 GFLOPS | Progress: (16/20) | 24.35 s
[Task 8/25] Current/Best: 10.67/ 19.91 GFLOPS | Progress: (20/20) | 32.45 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (4/20) | 3.60 s
[Task 9/25] Current/Best: 13.35/ 19.21 GFLOPS | Progress: (8/20) | 9.57 s
[Task 9/25] Current/Best: 15.26/ 20.74 GFLOPS | Progress: (12/20) | 13.38 s
[Task 9/25] Current/Best: 18.16/ 22.32 GFLOPS | Progress: (16/20) | 15.42 s
[Task 9/25] Current/Best: 18.45/ 22.32 GFLOPS | Progress: (20/20) | 23.61 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 4.59/ 18.44 GFLOPS | Progress: (4/20) | 3.88 s
[Task 10/25] Current/Best: 19.70/ 19.70 GFLOPS | Progress: (8/20) | 5.16 s
[Task 10/25] Current/Best: 14.98/ 20.27 GFLOPS | Progress: (12/20) | 7.48 s
[Task 10/25] Current/Best: 15.12/ 20.27 GFLOPS | Progress: (16/20) | 9.69 s
[Task 10/25] Current/Best: 7.56/ 20.27 GFLOPS | Progress: (20/20) | 11.54 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.85/ 14.23 GFLOPS | Progress: (4/20) | 4.61 s
[Task 11/25] Current/Best: 12.33/ 17.57 GFLOPS | Progress: (8/20) | 6.84 s
[Task 11/25] Current/Best: 10.29/ 17.57 GFLOPS | Progress: (12/20) | 9.14 s
[Task 11/25] Current/Best: 18.86/ 18.86 GFLOPS | Progress: (16/20) | 10.75 s
[Task 11/25] Current/Best: 14.26/ 18.86 GFLOPS | Progress: (20/20) | 13.48 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 11.62/ 11.62 GFLOPS | Progress: (4/20) | 6.17 s
[Task 12/25] Current/Best: 16.27/ 22.42 GFLOPS | Progress: (8/20) | 8.18 s
[Task 12/25] Current/Best: 13.09/ 22.42 GFLOPS | Progress: (12/20) | 13.36 s
[Task 12/25] Current/Best: 15.56/ 22.42 GFLOPS | Progress: (16/20) | 16.18 s
[Task 12/25] Current/Best: 7.39/ 22.42 GFLOPS | Progress: (20/20) | 19.32 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.52/ 21.45 GFLOPS | Progress: (4/20) | 4.10 s
[Task 13/25] Current/Best: 21.04/ 21.45 GFLOPS | Progress: (8/20) | 7.63 s
[Task 13/25] Current/Best: 11.56/ 21.45 GFLOPS | Progress: (12/20) | 10.64 s
[Task 13/25] Current/Best: 6.13/ 21.45 GFLOPS | Progress: (16/20) | 12.75 s
[Task 13/25] Current/Best: 5.95/ 21.80 GFLOPS | Progress: (20/20) | 15.97 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 5.28/ 10.64 GFLOPS | Progress: (4/20) | 4.22 s
[Task 14/25] Current/Best: 13.92/ 23.16 GFLOPS | Progress: (8/20) | 11.14 s
[Task 14/25] Current/Best: 5.08/ 23.16 GFLOPS | Progress: (12/20) | 18.41 s
[Task 14/25] Current/Best: 12.29/ 23.16 GFLOPS | Progress: (16/20) | 20.43 s
[Task 14/25] Current/Best: 9.51/ 23.16 GFLOPS | Progress: (20/20) | 24.60 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (4/20) | 4.99 s
[Task 15/25] Current/Best: 6.06/ 19.24 GFLOPS | Progress: (8/20) | 6.25 s
[Task 15/25] Current/Best: 11.41/ 19.24 GFLOPS | Progress: (12/20) | 13.46 s
[Task 15/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (16/20) | 14.99 s
[Task 15/25] Current/Best: 5.88/ 23.36 GFLOPS | Progress: (20/20) | 17.54 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 4.68/ 17.95 GFLOPS | Progress: (4/20) | 4.77 s
[Task 16/25] Current/Best: 6.62/ 17.95 GFLOPS | Progress: (8/20) | 6.24 s
[Task 16/25] Current/Best: 19.41/ 19.41 GFLOPS | Progress: (12/20) | 7.49 s
[Task 16/25] Current/Best: 16.20/ 19.41 GFLOPS | Progress: (16/20) | 9.06 s
[Task 16/25] Current/Best: 7.54/ 20.84 GFLOPS | Progress: (20/20)
| 12.50 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.96/ 13.25 GFLOPS | Progress: (4/20) | 4.58 s
[Task 17/25] Current/Best: 22.66/ 22.66 GFLOPS | Progress: (8/20) | 6.40 s
[Task 17/25] Current/Best: 7.04/ 22.66 GFLOPS | Progress: (12/20) | 8.79 s
[Task 17/25] Current/Best: 13.81/ 22.66 GFLOPS | Progress: (16/20) | 11.42 s
[Task 17/25] Current/Best: 13.26/ 22.66 GFLOPS | Progress: (20/20) | 13.81 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 8.86/ 17.46 GFLOPS | Progress: (4/20) | 5.74 s
[Task 18/25] Current/Best: 18.15/ 20.70 GFLOPS | Progress: (8/20) | 7.33 s
[Task 18/25] Current/Best: 19.93/ 20.70 GFLOPS | Progress: (12/20) | 9.52 s
[Task 18/25] Current/Best: 11.95/ 20.70 GFLOPS | Progress: (16/20) | 14.48 s
[Task 18/25] Current/Best: 5.61/ 22.73 GFLOPS | Progress: (20/20) | 16.95 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 13.91/ 16.93 GFLOPS | Progress: (4/20) | 5.43 s
[Task 19/25] Current/Best: 10.85/ 21.33 GFLOPS | Progress: (8/20) | 9.82 s
[Task 19/25] Current/Best: 20.08/ 21.68 GFLOPS | Progress: (12/20) | 12.42 s
[Task 19/25] Current/Best: 19.36/ 21.68 GFLOPS | Progress: (16/20) | 15.68 s
[Task 19/25] Current/Best: 7.95/ 21.68 GFLOPS | Progress: (20/20) | 18.15 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 1.58/ 20.21 GFLOPS | Progress: (4/20) | 4.64 s
[Task 20/25] Current/Best: 18.85/ 20.21 GFLOPS | Progress: (8/20) | 7.91 s
[Task 20/25] Current/Best: 10.35/ 20.21 GFLOPS | Progress: (12/20) | 10.88 s
[Task 20/25] Current/Best: 17.75/ 20.21 GFLOPS | Progress: (16/20) | 12.80 s
[Task 20/25] Current/Best: 17.98/ 20.21 GFLOPS | Progress: (20/20) | 13.92 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 14.28/ 14.28 GFLOPS | Progress: (4/20) | 8.80 s
[Task 1/25] Current/Best: 8.10/ 15.04 GFLOPS | Progress: (8/20) | 12.16 s
[Task 1/25] Current/Best: 11.14/ 15.04 GFLOPS | Progress: (12/20) | 14.36 s
[Task 1/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (16/20) | 16.23 s
[Task 1/25] Current/Best: 18.33/ 19.21 GFLOPS | Progress: (20/20) | 18.46 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.51/ 17.04 GFLOPS | Progress: (4/20) | 2.97 s
[Task 2/25] Current/Best: 7.17/ 17.73 GFLOPS | Progress: (8/20) | 4.14 s
[Task 2/25] Current/Best: 6.51/ 17.73 GFLOPS | Progress: (12/20) | 5.78 s
[Task 2/25] Current/Best: 10.08/ 17.73 GFLOPS | Progress: (16/20) | 7.13 s
[Task 2/25] Current/Best: 12.97/ 17.73 GFLOPS | Progress: (20/20) | 8.83 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 16.09/ 17.93 GFLOPS | Progress: (4/20) | 3.71 s
[Task 3/25] Current/Best: 8.21/ 19.50 GFLOPS | Progress: (8/20) | 6.07 s
[Task 3/25] Current/Best: 14.91/ 19.50 GFLOPS | Progress: (12/20) | 7.87 s
[Task 3/25] Current/Best: 13.03/ 20.20 GFLOPS | Progress: (16/20) | 9.84 s
[Task 3/25] Current/Best: 15.79/ 20.20 GFLOPS | Progress: (20/20) | 11.57 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 5.88/ 15.84 GFLOPS | Progress: (4/20) | 3.51 s
[Task 4/25] Current/Best: 21.69/ 21.69 GFLOPS | Progress: (8/20) | 5.87 s
[Task 4/25] Current/Best: 13.44/ 21.69 GFLOPS | Progress: (12/20) | 10.33 s
[Task 4/25] Current/Best: 11.59/ 21.69 GFLOPS | Progress: (16/20) | 12.95 s
[Task 4/25] Current/Best: 8.07/ 21.69 GFLOPS | Progress: (20/20) | 15.73 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 13.05/ 13.55 GFLOPS | Progress: (4/20) | 4.05 s
[Task 5/25] Current/Best: 7.19/ 16.26 GFLOPS | Progress: (8/20) | 6.13 s
[Task 5/25] Current/Best: 2.99/ 18.11 GFLOPS | Progress: (12/20) | 7.86 s
[Task 5/25] Current/Best: 3.50/ 18.11 GFLOPS | Progress: (16/20) | 9.84 s
[Task 5/25] Current/Best: 13.11/ 18.11 GFLOPS | Progress: (20/20) | 11.90 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.15/ 19.32 GFLOPS | Progress: (4/20) | 3.95 s
[Task 6/25] Current/Best: 8.70/ 19.32 GFLOPS | Progress: (8/20) | 6.64 s
[Task 6/25] Current/Best: 18.32/ 19.32 GFLOPS | Progress: (12/20) | 9.83 s
[Task 6/25] Current/Best: 14.27/ 19.76 GFLOPS | Progress: (16/20) | 11.56 s
[Task 6/25] Current/Best: 16.99/ 19.76 GFLOPS | Progress: (20/20) | 13.64 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 13.92/ 13.92 GFLOPS | Progress: (4/20) | 6.54 s
[Task 7/25] Current/Best: 17.55/ 21.93 GFLOPS | Progress: (8/20) | 8.69 s
[Task 7/25] Current/Best: 18.20/ 21.93 GFLOPS | Progress: (12/20) | 10.81 s
[Task 7/25] Current/Best: 17.68/ 22.22 GFLOPS | Progress: (16/20) | 12.77 s
[Task 7/25] Current/Best: 14.90/ 22.22 GFLOPS | Progress: (20/20) | 14.58 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.04/ 12.93 GFLOPS | Progress: (4/20) | 7.62 s
[Task 8/25] Current/Best: 2.75/ 21.99 GFLOPS | Progress: (8/20) | 19.84 s
[Task 8/25] Current/Best: 11.76/ 21.99 GFLOPS | Progress: (12/20) | 23.48 s
[Task 8/25] Current/Best: 10.54/ 21.99 GFLOPS | Progress: (16/20) | 28.00 s
[Task 8/25] Current/Best: 18.28/ 21.99 GFLOPS | Progress: (20/20) | 32.40 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 17.85/ 19.20 GFLOPS | Progress: (4/20) | 3.24 s
[Task 9/25] Current/Best: 8.24/ 20.61 GFLOPS | Progress: (8/20) | 5.92 s
[Task 9/25] Current/Best: 6.69/ 20.61 GFLOPS | Progress: (12/20) | 8.01 s
[Task 9/25] Current/Best: 11.54/ 22.83 GFLOPS | Progress: (16/20) | 12.59 s
[Task 9/25] Current/Best: 8.25/ 22.83 GFLOPS | Progress: (20/20) | 16.53 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 8.68/ 16.37 GFLOPS | Progress: (4/20) | 3.38 s
[Task 10/25] Current/Best: 5.87/ 16.37 GFLOPS | Progress: (8/20) | 5.06 s
[Task 10/25] Current/Best: 1.59/ 17.73 GFLOPS | Progress: (12/20) | 7.11 s
[Task 10/25] Current/Best: 18.44/ 18.44 GFLOPS | Progress: (16/20) | 8.82 s
[Task 10/25] Current/Best: 7.77/ 18.44 GFLOPS | Progress: (20/20) | 10.59 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 15.89/ 21.34 GFLOPS | Progress: (4/20) | 3.80 s
[Task 11/25] Current/Best: 3.13/ 21.34 GFLOPS | Progress: (8/20) | 8.09 s
[Task 11/25] Current/Best: 13.42/ 21.34 GFLOPS | Progress: (12/20) | 10.41 s
[Task 11/25] Current/Best: 6.70/ 21.34 GFLOPS | Progress: (16/20) | 12.57 s
[Task 11/25] Current/Best: 23.24/ 24.01 GFLOPS | Progress: (20/20) | 14.63 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 5.41/ 12.97 GFLOPS | Progress: (4/20) | 4.45 s
[Task 12/25] Current/Best: 12.21/ 18.07 GFLOPS | Progress: (8/20) | 7.14 s
[Task 12/25] Current/Best: 9.42/ 21.29 GFLOPS | Progress: (12/20) | 10.58 s
[Task 12/25] Current/Best: 13.51/ 21.29 GFLOPS | Progress: (16/20) | 13.13 s
[Task 12/25] Current/Best: 15.60/ 21.29 GFLOPS | Progress: (20/20) | 14.81 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.93/ 16.57 GFLOPS | Progress: (4/20) | 4.11 s
[Task 13/25] Current/Best: 12.04/ 19.36 GFLOPS | Progress: (8/20) | 6.97 s
[Task 13/25] Current/Best: 16.60/ 19.36 GFLOPS | Progress: (12/20) | 8.85 s
[Task 13/25] Current/Best: 15.69/ 21.65 GFLOPS | Progress: (16/20) | 11.48 s
[Task 13/25] Current/Best: 9.88/ 21.65 GFLOPS | Progress: (20/20) | 14.53 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 9.59/ 12.33 GFLOPS | Progress: (4/20) | 3.89 s
[Task 14/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (8/20) | 7.96 s
[Task 14/25] Current/Best: 3.11/ 20.86 GFLOPS | Progress: (12/20) | 9.59 s
[Task 14/25] Current/Best: 12.88/ 20.86 GFLOPS | Progress: (16/20) | 13.50 s
[Task 14/25] Current/Best: 14.21/ 20.86 GFLOPS | Progress: (20/20) | 17.29 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 21.04/ 21.04 GFLOPS | Progress: (4/20) | 3.14 s
[Task 15/25] Current/Best: 11.58/ 21.04 GFLOPS | Progress: (8/20) | 7.09 s
[Task 15/25] Current/Best: 15.09/ 21.04 GFLOPS | Progress: (12/20) | 10.38 s
[Task 15/25] Current/Best: 5.80/ 21.04 GFLOPS | Progress: (16/20) | 18.86 s
[Task 15/25] Current/Best: 16.47/ 21.04 GFLOPS | Progress: (20/20)
| 20.99 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 21/25] Current/Best: 9.81/ 10.76 GFLOPS | Progress: (4/20) | 4.97 s
[Task 21/25] Current/Best: 5.19/ 21.05 GFLOPS | Progress: (8/20) | 6.38 s
[Task 21/25] Current/Best: 20.28/ 21.05 GFLOPS | Progress: (12/20) | 8.48 s
[Task 21/25] Current/Best: 16.55/ 21.05 GFLOPS | Progress: (16/20) | 11.06 s
[Task 21/25] Current/Best: 12.66/ 21.05 GFLOPS | Progress: (20/20) | 12.39 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 7.60/ 18.20 GFLOPS | Progress: (4/20) | 4.95 s
[Task 22/25] Current/Best: 11.65/ 18.20 GFLOPS | Progress: (8/20) | 6.66 s
[Task 22/25] Current/Best: 16.19/ 20.88 GFLOPS | Progress: (12/20) | 7.91 s
[Task 22/25] Current/Best: 2.69/ 20.88 GFLOPS | Progress: (16/20) | 10.08 s
[Task 22/25] Current/Best: 4.16/ 20.88 GFLOPS | Progress: (20/20) | 12.06 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.88/ 14.01 GFLOPS | Progress: (4/20) | 6.24 s
[Task 23/25] Current/Best: 11.86/ 18.11 GFLOPS | Progress: (8/20) | 9.93 s
[Task 23/25] Current/Best: 8.25/ 18.19 GFLOPS | Progress: (12/20) | 13.06 s
[Task 23/25] Current/Best: 9.89/ 18.19 GFLOPS | Progress: (16/20) | 14.95 s
[Task 23/25] Current/Best: 13.52/ 18.19 GFLOPS | Progress: (20/20) | 18.43 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 2.07/ 8.92 GFLOPS | Progress: (4/20) | 12.63 s
[Task 24/25] Current/Best: 5.51/ 8.92 GFLOPS | Progress: (8/20) | 24.30 s
[Task 24/25] Current/Best: 3.96/ 8.92 GFLOPS | Progress: (12/20) | 36.19 s
[Task 24/25] Current/Best: 1.10/ 8.92 GFLOPS | Progress: (16/20) | 43.10 s Done.
-
[Task 24/25] Current/Best: 3.58/ 8.92 GFLOPS | Progress: (20/20) | 53.77 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.69/ 5.69 GFLOPS | Progress: (4/20) | 12.55 s
[Task 25/25] Current/Best: 1.55/ 7.50 GFLOPS | Progress: (8/20) | 23.28 s
[Task 25/25] Current/Best: 1.55/ 10.12 GFLOPS | Progress: (12/20) | 25.24 s
[Task 25/25] Current/Best: 4.99/ 10.12 GFLOPS | Progress: (16/20) | 35.96 s
[Task 25/25] Current/Best: 1.53/ 10.12 GFLOPS | Progress: (20/20) | 42.25 s
+
[Task 16/25] Current/Best: 14.95/ 15.60 GFLOPS | Progress: (4/20) | 4.84 s
[Task 16/25] Current/Best: 16.16/ 22.60 GFLOPS | Progress: (8/20) | 6.39 s
[Task 16/25] Current/Best: 4.36/ 22.60 GFLOPS | Progress: (12/20) | 8.76 s
[Task 16/25] Current/Best: 12.34/ 22.60 GFLOPS | Progress: (16/20) | 10.55 s
[Task 16/25] Current/Best: 16.10/ 22.60 GFLOPS | Progress: (20/20) | 11.85 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 6.17/ 6.44 GFLOPS | Progress: (4/20) | 4.59 s
[Task 17/25] Current/Best: 6.17/ 19.28 GFLOPS | Progress: (8/20) | 7.73 s
[Task 17/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (12/20) | 10.22 s
[Task 17/25] Current/Best: 10.56/ 20.50 GFLOPS | Progress: (16/20) | 12.75 s
[Task 17/25] Current/Best: 23.65/ 23.65 GFLOPS | Progress: (20/20) | 14.80 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 5.09/ 11.53 GFLOPS | Progress: (4/20) | 7.89 s
[Task 18/25] Current/Best: 6.53/ 17.63 GFLOPS | Progress: (8/20) | 11.25 s
[Task 18/25] Current/Best: 12.08/ 17.63 GFLOPS | Progress: (12/20) | 15.62 s
[Task 18/25] Current/Best: 10.87/ 20.10 GFLOPS | Progress: (16/20) | 19.43 s
[Task 18/25] Current/Best: 12.15/ 20.10 GFLOPS | Progress: (20/20) | 22.11 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.63/ 11.16 GFLOPS | Progress: (4/20) | 5.18 s
[Task 19/25] Current/Best: 8.37/ 21.71 GFLOPS | Progress: (8/20) | 10.09 s
[Task 19/25] Current/Best: 10.02/ 22.09 GFLOPS | Progress: (12/20) | 12.61 s
[Task 19/25] Current/Best: 20.95/ 22.09 GFLOPS | Progress: (16/20) | 16.25 s
[Task 19/25] Current/Best: 12.21/ 22.09 GFLOPS | Progress: (20/20) | 18.70 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.66/ 19.68 GFLOPS | Progress: (4/20) | 4.28 s
[Task 20/25] Current/Best: 12.98/ 19.68 GFLOPS | Progress: (8/20) | 6.01 s
[Task 20/25] Current/Best: 4.54/ 19.68 GFLOPS | Progress: (12/20) | 8.60 s
[Task 20/25] Current/Best: 6.47/ 19.68 GFLOPS | Progress: (16/20) | 11.41 s
[Task 20/25] Current/Best: 5.02/ 19.68 GFLOPS | Progress: (20/20) | 12.99 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 16.65/ 16.65 GFLOPS | Progress: (4/20) | 4.09 s
[Task 21/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (8/20) | 6.77 s
[Task 21/25] Current/Best: 8.72/ 20.22 GFLOPS | Progress: (12/20) | 9.39 s
[Task 21/25] Current/Best: 10.80/ 20.22 GFLOPS | Progress: (16/20) | 10.84 s
[Task 21/25] Current/Best: 19.05/ 20.22 GFLOPS | Progress: (20/20)
| 13.64 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 22/25] Current/Best: 13.77/ 20.39 GFLOPS | Progress: (4/20) | 4.01 s
[Task 22/25] Current/Best: 10.30/ 20.39 GFLOPS | Progress: (8/20) | 6.59 s
[Task 22/25] Current/Best: 4.74/ 20.39 GFLOPS | Progress: (12/20) | 8.67 s
[Task 22/25] Current/Best: 15.89/ 20.39 GFLOPS | Progress: (16/20) | 10.27 s
[Task 22/25] Current/Best: 16.17/ 20.39 GFLOPS | Progress: (20/20) | 11.52 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 15.16/ 20.79 GFLOPS | Progress: (4/20) | 4.55 s
[Task 23/25] Current/Best: 11.88/ 20.79 GFLOPS | Progress: (8/20) | 7.51 s
[Task 23/25] Current/Best: 11.78/ 20.79 GFLOPS | Progress: (12/20) | 10.01 s
[Task 23/25] Current/Best: 7.99/ 23.84 GFLOPS | Progress: (16/20) | 12.90 s
[Task 23/25] Current/Best: 8.92/ 23.84 GFLOPS | Progress: (20/20) | 15.41 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 10.64/ 10.64 GFLOPS | Progress: (4/20) | 12.57 s
[Task 24/25] Current/Best: 8.91/ 10.64 GFLOPS | Progress: (8/20) | 24.01 s
[Task 24/25] Current/Best: 3.46/ 10.64 GFLOPS | Progress: (12/20) | 29.44 s
[Task 24/25] Current/Best: 4.62/ 10.64 GFLOPS | Progress: (16/20) | 36.82 s
[Task 24/25] Current/Best: 7.48/ 10.64 GFLOPS | Progress: (20/20) | 47.32 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 6.45 GFLOPS | Progress: (4/20) | 4.79 s Done.
+
[Task 25/25] Current/Best: 5.30/ 9.35 GFLOPS | Progress: (8/20) | 5.83 s
[Task 25/25] Current/Best: 8.66/ 9.35 GFLOPS | Progress: (12/20) | 16.52 s
[Task 25/25] Current/Best: 3.88/ 9.35 GFLOPS | Progress: (16/20) | 28.25 s
[Task 25/25] Current/Best: 6.60/ 9.35 GFLOPS | Progress: (20/20) | 33.81 s
@@ -673,8 +674,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621102
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -731,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 413.91314563999913, 'median': 412.91996579999477, 'std': 3.3961179297374042}
- unoptimized: {'mean': 513.5714736600005, 'median': 514.0005617999975, 'std': 2.4411642308100787}
+ optimized: {'mean': 399.3069681899942, 'median': 398.9944450499934, 'std': 1.3445116509085404}
+ unoptimized: {'mean': 512.2266732599974, 'median': 511.84938844999124, 'std': 2.0156171937905514}
@@ -755,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 13.309 seconds)
+ **Total running time of the script:** ( 10 minutes 41.748 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 7e0d705e7f..aaac3b71ac 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
- 1.192e-07 secs/op
+ 1.51e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index a717d78811..67094dcdad 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, 0x219f37d0)), stage(b, placeholder(b, 0xa269d30)), 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, 0x8de4250)), stage(b, placeholder(b, 0x10a1a8c0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index b3c2974d87..f29447bac0 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,32 +5,32 @@
Computation times
=================
-**14:20.069** total execution time for **tutorial** files:
+**13:38.699** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:13.309 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:41.748 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:03.828 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:02.702 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.146 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.183 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.143 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.263 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:29.591 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.127 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.177 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.790 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.710 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.712 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_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 |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 01fd1b5556..f9a591f170 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,8 +294,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000008
+ Numpy running time: 0.000011
+ naive: 0.000009
@@ -394,7 +394,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000008
@@ -501,10 +501,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.71974999906888e-06 1.0
- naive 7.6063e-06 0.9853039283548607
- parallel 6.915799999999999e-06 0.8958580265985492
- vector 2.4570100000000004e-05 3.182758509402964
+ numpy 1.1248790005993215e-05 1.0
+ naive 8.7647e-06 0.7791682479031324
+ parallel 8.1072e-06 0.7207175167889688
+ vector 2.45778e-05 2.184928333350099
@@ -925,7 +925,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018207
+ Numpy running time: 0.019156
@@ -983,7 +983,7 @@ optimizations.
.. code-block:: none
- none: 3.196889
+ none: 3.427616
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.297512
+ blocking: 0.302070
@@ -1182,7 +1182,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.339053
+ vectorization: 0.335691
@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], []),
@@ -1256,7 +1256,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118813
+ loop permutation: 0.114591
@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], []),
@@ -1355,7 +1355,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.110212
+ array packing: 0.108109
@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], []),
@@ -1448,7 +1448,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110974
+ block caching: 0.110276
@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], []),
@@ -1534,7 +1534,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147122
+ parallelization: 0.146313
@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], []),
@@ -1615,13 +1615,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.1968892895 1.0
- blocking 0.29751210190000005 0.09306299810792995
- vectorization 0.3390527557 0.10605708393268398
- loop permutation 0.11881302 0.03716519692759914
- array packing 0.11021195749999999 0.03447474952041187
- block caching 0.11097361080000001 0.03471299777708489
- parallelization 0.14712218700000002 0.04602041975091675
+ none 3.4276162451999994 1.0
+ blocking 0.3020695814 0.0881281799918574
+ vectorization 0.3356909334 0.0979371403873168
+ loop permutation 0.11459137479999999 0.03343179825351588
+ array packing 0.1081091882 0.031540633625889436
+ block caching 0.1102759606 0.032172785023536224
+ parallelization 0.14631276399999998 0.042686448404162795
@@ -1661,6 +1661,11 @@ 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 1.183 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index c984e18624..3debcbc794 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b61f633e10b02ac3e767ad268562a4dd2c178de5
+7a4c10c44a9255ac2fa52ce7e3a83f718d60823f
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 743b3c806e..e45903e2a6 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -572,7 +572,7 @@ 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 12.001 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.928 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_keras.html b/docs/how_to/compile_models/from_keras.html
index 0b930d1074..3cd2596437 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -493,7 +493,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 942ms/step
+1/1 [==============================] - 1s 946ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 7d509cefa5..f03dc81bbe 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.zipfc9dc6c1-d731-4bae-8015-b5cf3e9e8b9b 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.zipb02da895-219d-4f55-a72e-696c202702f9 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index 9567b81d55..74da188db3 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -435,14 +435,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<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, 46.9MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 34.2MB/s]
- 43%|####2 | 17.7M/41.5M [00:00<00:00, 33.8MB/s]
- 54%|#####3 | 22.3M/41.5M [00:00<00:00, 30.4MB/s]
- 61%|###### | 25.3M/41.5M [00:00<00:00, 29.2MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.3MB/s]
- 96%|#########6| 40.0M/41.5M [00:01<00:00, 46.7MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 40.4MB/s]
+ 16%|#6 | 6.76M/41.5M [00:00<00:00, 70.9MB/s]
+ 33%|###2 | 13.5M/41.5M [00:00<00:00, 56.2MB/s]
+ 48%|####8 | 19.9M/41.5M [00:00<00:00, 60.6MB/s]
+ 62%|######2 | 25.9M/41.5M [00:00<00:00, 47.8MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 50.5MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 39.0MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 47.0MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index e11ca9a8f9..3df06d8d12 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,21 +414,11 @@ 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]
- 1%| | 440k/44.7M [00:00<00:10, 4.34MB/s]
- 3%|2 | 1.12M/44.7M [00:00<00:07, 5.97MB/s]
- 4%|4 | 1.95M/44.7M [00:00<00:06, 7.17MB/s]
- 7%|6 | 2.98M/44.7M [00:00<00:05, 8.61MB/s]
- 10%|9 | 4.29M/44.7M [00:00<00:04, 10.3MB/s]
- 13%|#3 | 5.98M/44.7M [00:00<00:03, 12.8MB/s]
- 18%|#7 | 8.00M/44.7M [00:00<00:02, 15.5MB/s]
- 24%|##3 | 10.6M/44.7M [00:00<00:01, 19.2MB/s]
- 31%|### | 13.8M/44.7M [00:00<00:01, 23.7MB/s]
- 40%|#### | 17.9M/44.7M [00:01<00:00, 29.5MB/s]
- 51%|#####1 | 22.9M/44.7M [00:01<00:00, 36.5MB/s]
- 65%|######5 | 29.1M/44.7M [00:01<00:00, 45.0MB/s]
- 81%|######## | 36.1M/44.7M [00:01<00:00, 53.4MB/s]
- 97%|#########6| 43.3M/44.7M [00:01<00:00, 60.1MB/s]
-100%|##########| 44.7M/44.7M [00:01<00:00, 32.7MB/s]
+ 11%|#1 | 4.95M/44.7M [00:00<00:00, 51.9MB/s]
+ 22%|##2 | 9.91M/44.7M [00:00<00:00, 51.3MB/s]
+ 59%|#####9 | 26.4M/44.7M [00:00<00:00, 107MB/s]
+ 97%|#########7| 43.4M/44.7M [00:00<00:00, 135MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 115MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 2c2b60de6d..807cf55d20 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -632,7 +632,7 @@ 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 10.510 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.567 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 55333eef7c..f18903307f 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">ΒΆ</a></h1>
-<p><strong>05:38.701</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:35.183</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>01:12.001</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>01:11.567</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>01:10.510</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>01:09.928</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>00:45.326</p></td>
+<td><p>00:44.462</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>00:30.283</p></td>
+<td><p>00:30.865</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:28.400</p></td>
+<td><p>00:27.709</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>00:25.603</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:25.167</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>00:25.107</p></td>
+<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>00:24.732</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>00:23.489</p></td>
+<td><p>00:22.113</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>00:15.071</p></td>
+<td><p>00:16.164</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>00:02.911</p></td>
+<td><p>00:02.476</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 6dcac6f44f..ef60ca0173 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -649,7 +649,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9066 15.8665 16.2268 15.6885 0.1617
+ 16.0986 15.6962 19.4010 15.5811 1.1109
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
index f3cd0236e5..57a09f487c 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,14 +436,13 @@ 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]
- 6%|5 | 9.45M/170M [00:00<00:01, 99.1MB/s]
- 17%|#6 | 28.7M/170M [00:00<00:00, 159MB/s]
- 33%|###3 | 56.1M/170M [00:00<00:00, 218MB/s]
- 49%|####9 | 84.0M/170M [00:00<00:00, 247MB/s]
- 68%|######7 | 115M/170M [00:00<00:00, 277MB/s]
- 84%|########3 | 142M/170M [00:00<00:00, 251MB/s]
- 98%|#########7| 166M/170M [00:00<00:00, 241MB/s]
-100%|##########| 170M/170M [00:00<00:00, 234MB/s]
+ 11%|# | 17.9M/170M [00:00<00:00, 187MB/s]
+ 26%|##6 | 44.2M/170M [00:00<00:00, 240MB/s]
+ 42%|####1 | 71.2M/170M [00:00<00:00, 259MB/s]
+ 57%|#####7 | 97.6M/170M [00:00<00:00, 266MB/s]
+ 73%|#######2 | 124M/170M [00:00<00:00, 270MB/s]
+ 89%|########8 | 150M/170M [00:00<00:00, 272MB/s]
+100%|##########| 170M/170M [00:00<00:00, 264MB/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').
@@ -537,7 +536,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.006 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.456 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 bd19c93f7b..68597bfde8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,8 +480,9 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 83%|########3 | 11.3M/13.6M [00:00<00:00, 118MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 130MB/s]
+ 30%|### | 4.07M/13.6M [00:00<00:00, 42.6MB/s]
+ 63%|######2 | 8.52M/13.6M [00:00<00:00, 45.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 62.2MB/s]
</pre></div>
</div>
</div>
@@ -566,7 +567,7 @@ 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)
- 90.3860 90.2612 93.0289 90.0348 0.4464
+ 90.2022 90.1283 94.2429 89.8640 0.4784
</pre></div>
</div>
<div class="admonition note">
@@ -605,7 +606,7 @@ 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">ΒΆ</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.466 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.489 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 d228daf665..90fe06ec91 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -569,7 +569,7 @@ 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)
- 120.3369 120.1555 122.8037 119.4390 0.5698
+ 119.6808 119.7133 123.9559 117.4201 0.7975
</pre></div>
</div>
<div class="admonition note">
@@ -597,7 +597,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 0.036 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.873 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 9af9038827..73bf0c2e95 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -507,7 +507,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.954 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.969 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 7a58f50ade..072bfb408f 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]
- 5%|4 | 6131/132723 [00:00<00:02, 61300.27KB/s]
- 10%|# | 13666/132723 [00:00<00:01, 69552.71KB/s]
- 16%|#5 | 20622/132723 [00:00<00:02, 47843.65KB/s]
- 21%|##1 | 28029/132723 [00:00<00:01, 55963.72KB/s]
- 27%|##6 | 35428/132723 [00:00<00:01, 61490.62KB/s]
- 32%|###2 | 42868/132723 [00:00<00:01, 65421.43KB/s]
- 38%|###7 | 50334/132723 [00:00<00:01, 68222.02KB/s]
- 43%|####3 | 57682/132723 [00:00<00:01, 69809.60KB/s]
- 49%|####8 | 64849/132723 [00:01<00:00, 69673.64KB/s]
- 54%|#####4 | 72233/132723 [00:01<00:00, 70918.02KB/s]
- 60%|###### | 79678/132723 [00:01<00:00, 71972.54KB/s]
- 66%|######5 | 87179/132723 [00:01<00:00, 72880.21KB/s]
- 71%|#######1 | 94708/132723 [00:01<00:00, 73599.84KB/s]
- 77%|#######7 | 102257/132723 [00:01<00:00, 74155.25KB/s]
- 83%|########2 | 109842/132723 [00:01<00:00, 74661.84KB/s]
- 88%|########8 | 117431/132723 [00:01<00:00, 74996.51KB/s]
- 94%|#########4| 125045/132723 [00:01<00:00, 75337.36KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75633.38KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 69683.67KB/s]
+ 5%|4 | 6036/132723 [00:00<00:02, 60351.42KB/s]
+ 10%|# | 13557/132723 [00:00<00:01, 67968.73KB/s]
+ 16%|#5 | 20904/132723 [00:00<00:01, 70454.30KB/s]
+ 21%|##1 | 28408/132723 [00:00<00:01, 72251.59KB/s]
+ 27%|##6 | 35814/132723 [00:00<00:01, 72898.32KB/s]
+ 33%|###2 | 43352/132723 [00:00<00:01, 73737.68KB/s]
+ 38%|###8 | 50913/132723 [00:00<00:01, 74345.18KB/s]
+ 44%|####3 | 58348/132723 [00:00<00:01, 73729.56KB/s]
+ 50%|####9 | 65891/132723 [00:00<00:00, 74256.67KB/s]
+ 55%|#####5 | 73444/132723 [00:01<00:00, 74645.94KB/s]
+ 61%|######1 | 81082/132723 [00:01<00:00, 75173.31KB/s]
+ 67%|######6 | 88601/132723 [00:01<00:00, 74866.91KB/s]
+ 72%|#######2 | 96152/132723 [00:01<00:00, 75058.67KB/s]
+ 78%|#######8 | 103763/132723 [00:01<00:00, 75373.25KB/s]
+ 84%|########4 | 111493/132723 [00:01<00:00, 75947.88KB/s]
+ 90%|########9 | 119225/132723 [00:01<00:00, 76359.38KB/s]
+ 96%|#########5| 126984/132723 [00:01<00:00, 76727.11KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 74541.48KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -498,7 +497,7 @@ 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 48.350 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 46.443 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 41274b388e..0354cd9f72 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">ΒΆ</a></h1>
-<p><strong>12:12.344</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:56.099</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,39 +336,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:07.006</p></td>
+<td><p>03:04.456</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>02:48.350</p></td>
+<td><p>02:46.443</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:00.036</p></td>
+<td><p>01:53.873</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>01:32.954</p></td>
+<td><p>01:30.969</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>01:19.466</p></td>
+<td><p>01:17.489</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>00:35.200</p></td>
+<td><p>00:34.820</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>00:24.900</p></td>
+<td><p>00:24.270</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>00:24.426</p></td>
+<td><p>00:23.773</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index d28e380d24..23378e77fc 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -608,7 +608,7 @@ 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.zip69f95595-c52c-4684-b263-83c405e4a374 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.zipa98ba8ef-1d98-45bd-bcb4-3fb39158bd78 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>Itβs easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 5637a450b0..78691bdecd 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">ΒΆ</a></h1>
-<p><strong>00:44.734</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:44.639</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:41.403</p></td>
+<td><p>00:41.304</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>00:02.332</p></td>
+<td><p>00:02.340</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>00:00.991</p></td>
+<td><p>00:00.986</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 69d50e3ffb..09253aabb0 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: 6858us [6858us] (46.21%; 46.21%)
-FoldScaleAxis: 7982us [6us] (53.79%; 53.79%)
- FoldConstant: 7976us [1646us] (53.75%; 99.93%)
- InferType: 6329us [6329us] (42.65%; 79.36%)
+InferType: 6689us [6689us] (46.04%; 46.04%)
+FoldScaleAxis: 7840us [5us] (53.96%; 53.96%)
+ FoldConstant: 7835us [1639us] (53.93%; 99.94%)
+ InferType: 6196us [6196us] (42.65%; 79.08%)
</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: 6295us [6295us] (44.48%; 44.48%)
-FoldScaleAxis: 7859us [5us] (55.52%; 55.52%)
- FoldConstant: 7854us [1622us] (55.49%; 99.94%)
- InferType: 6232us [6232us] (44.03%; 79.35%)
+InferType: 6249us [6249us] (44.48%; 44.48%)
+FoldScaleAxis: 7801us [4us] (55.52%; 55.52%)
+ FoldConstant: 7797us [1632us] (55.49%; 99.95%)
+ InferType: 6165us [6165us] (43.88%; 79.07%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index 67ed542a19..8a81f5d4ff 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: 35.307552 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.713310 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 7ac8216e29..183784f11c 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: 13.351926 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.861722 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 407fa393ed..43420d7d9d 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: 0.018546
-Baseline: 3.254144
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017874
+Baseline: 3.452391
</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: 0.303355
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.293947
</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: 0.336773
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332670
</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: 0.115589
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114966
</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: 0.109823
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109266
</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: 0.111114
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111201
</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: 0.146586
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145125
</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 6e7f32c1e4..af9ab7ab7c 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">ΒΆ</a></h1>
-<p><strong>00:34.197</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.410</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>00:31.821</p></td>
+<td><p>00:32.077</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>00:01.354</p></td>
+<td><p>00:01.272</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.022</p></td>
+<td><p>00:01.061</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 f63e6562b6..88421e9ef8 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">ΒΆ</a></h1>
-<p><strong>06:53.002</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:39.802</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>03:40.678</p></td>
+<td><p>03:29.614</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>01:29.211</p></td>
+<td><p>01:29.247</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>00:59.377</p></td>
+<td><p>00:58.886</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>00:22.883</p></td>
+<td><p>00:21.208</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>00:10.488</p></td>
+<td><p>00:10.592</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>00:10.365</p></td>
+<td><p>00:10.255</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 ba2df4b0d9..020c40673e 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
@@ -491,205 +491,1156 @@ 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" = 32;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), 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" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 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
- for (rc.outer.outer: int32, 0, 8) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*3136)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*576)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 112), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 224), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 336), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 448), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 560), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 672), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 896), 9)*7)) + cse_var_3) + 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 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 776)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1120), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1232), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1344), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1456), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1680), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1792), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1904), 9)*7)) + cse_var_3) + 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 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1560)], 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2128), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2240), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2352), 9)*7)) + cse_var_3) + 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(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2464), 9)*7)) + cse_var_3) + 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 + 2576)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2576), 9)*7)) + cse_var_3) + 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 + 2688)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2688), 9)*7)) + cse_var_3) + 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 + 2800)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2800), 9)*7)) + cse_var_3) + 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 + 2912)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 2912), 9)*7)) + cse_var_3) + 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 + 3024)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 2344)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 49), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3136), 9)*7)) + cse_var_3) + 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 + 3248)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 35), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3248), 9)*7)) + cse_var_3) + 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 + 3360)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 21), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3360), 9)*7)) + cse_var_3) + 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 + 3472)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 7), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3472), 9)*7)) + cse_var_3) + 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 + 3584)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 56), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3584), 9)*7)) + cse_var_3) + 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 + 3696)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 42), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3696), 9)*7)) + cse_var_3) + 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 + 3808)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 28), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3808), 9)*7)) + cse_var_3) + 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 + 3920)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 14), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 3920), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 48), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 672), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1008), 192)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1232), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1456), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1680), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 48), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1792), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1904), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 176), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2016), 192)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 64)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2128), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2240), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 192)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 16)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2464), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 160), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2576), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2800), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2912), 192)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 48), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3024), 192)*4608)) + cse_var_2) + ((floordiv(threadIdx.x_2, 3) + 48)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*24)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod((threadIdx.x_1*24), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod((threadIdx. [...]
}
- for (rc.outer.inner: int32, 0, 32) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 66)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 67)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 68)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 69)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*126) + (floormod(threadIdx.x, 7)*9)) + 71)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + (rc.outer.inner*6)) + 5)]))
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) - 8)], 0f32, dtype=float32)
}
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*8), 27)) && (floormod(((threadIdx.x_1*24) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv((threadIdx.x_1*8), 27)*49)) + (floordiv(floormod((threadIdx.x_1*8), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 1), 27)) && (floormod(((threadIdx.x_1*24) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 2), 27)) && (floormod(((threadIdx.x_1*24) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f32, [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtype= [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)) && (floormod(((threadIdx.x_1*24) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 12)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 13)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 14)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 4), 27)) && (floormod(((threadIdx.x_1*24) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 4), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 4), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 15)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 6), 9))) && (floormod(((threadIdx.x_1*6) + 6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 6), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 16)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 7), 9))) && (floormod(((threadIdx.x_1*6) + 7), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 7), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 17)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 5), 27)) && (floormod(((threadIdx.x_1*24) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 8), 9))) && (floormod(((threadIdx.x_1*6) + 8), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 5), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 5), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 8), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 18)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*6), 9))) && (floormod((threadIdx.x_1*6), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*6), 9)) - 8)], 0f32, dtyp [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 19)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 1), 9))) && (floormod(((threadIdx.x_1*6) + 1), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 1), 9)) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 20)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)) && (floormod(((threadIdx.x_1*24) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 2), 9))) && (floormod(((threadIdx.x_1*6) + 2), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 6), 27)*49)) + (floormod((floordiv((threadIdx.x_1*8), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*6) + 2), 9)) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 21)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 3), 9))) && (floormod(((threadIdx.x_1*6) + 3), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 3), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 22)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 4), 9))) && (floormod(((threadIdx.x_1*6) + 4), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*24) + 23)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*8) + 7), 27)) && (floormod(((threadIdx.x_1*24) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*6) + 5), 9))) && (floormod(((threadIdx.x_1*6) + 5), 9) < 8)), data[(((((rc.outer.outer*784) + (floordiv(((threadIdx.x_1*8) + 7), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*8) + 7), 27), 3)*7)) + floormod(((threadIdx.x_1*6) + 5), 9)) - 8)], 0f3 [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
+ if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
}
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 22)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 23)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 24)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 25)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 26)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 84)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 85)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 86)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 87)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 88)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 89)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 93)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 94)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 95)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 96)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 97)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 98)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 102)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 103)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 104)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 105)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 106)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 107)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 165)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 166)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 167)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 168)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 169)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 170)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 174)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 175)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 176)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 177)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 178)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 179)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 183)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 184)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 185)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 186)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 187)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 188)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 246)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 247)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 248)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 249)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 250)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 251)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 336)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 337)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 338)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 339)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 340)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 341)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 345)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 346)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 347)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 348)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 349)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 350)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 408)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 409)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 410)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 411)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 412)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 413)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 417)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 418)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 419)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 420)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 421)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 422)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 426)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 427)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 428)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 429)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 430)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 431)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 489)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 490)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 491)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 492)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 493)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 494)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 498)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 499)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 500)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 501)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 502)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 503)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 588)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 589)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 590)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 591)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 592)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 593)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 655)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 651)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 652)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 653)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 654)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 655)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 656)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 660)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 661)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 662)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 663)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 660)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 661)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 662)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 663)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 664)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 660)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 661)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 662)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 663)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 664)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 665)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 669)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 670)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 671)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 672)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 669)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 670)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 671)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 672)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 673)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 669)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 670)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 671)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 672)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 673)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 674)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 732)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 733)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 734)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 732)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 733)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 734)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 736)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 732)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 733)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 734)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 735)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 736)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 737)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 741)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 742)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 743)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 744)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 741)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 742)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 743)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 744)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 745)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 741)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 742)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 743)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 744)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 745)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 746)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 750)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 751)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 752)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 753)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 750)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 751)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 752)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 753)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 754)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 750)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 751)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 752)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 753)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 754)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 755)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 813)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 814)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 815)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 816)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 813)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 814)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 815)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 816)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 817)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 813)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 814)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 815)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 816)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 817)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 818)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 907)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 903)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 904)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 905)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 906)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 907)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 908)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 912)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 913)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 914)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 915)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 912)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 913)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 914)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 915)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 916)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 912)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 913)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 914)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 915)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 916)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 917)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 975)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 976)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 977)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 978)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 975)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 976)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 977)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 978)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 979)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 975)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 976)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 977)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 978)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 979)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 980)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 984)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 985)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 986)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 987)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 984)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 985)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 986)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 987)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 988)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 984)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 985)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 986)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 987)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 988)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 989)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 993)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 994)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 995)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 996)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 993)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 994)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 995)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 996)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 997)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 993)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 994)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 995)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 996)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 997)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 998)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1053)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1056)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1057)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1058)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1059)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1056)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1057)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1058)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1059)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1060)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1056)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1057)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1058)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1059)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1060)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1061)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1062)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1065)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1066)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1067)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1068)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1065)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1066)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1067)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1068)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1069)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1065)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1066)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1067)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1068)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1069)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1070)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1074)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1075)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1076)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1077)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1079)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1147)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1149)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1150)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1151)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1156)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1157)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1158)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1156)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1157)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1158)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1159)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1156)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1157)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1158)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1159)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1160)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1219)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1220)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1221)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1219)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1220)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1221)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1222)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1219)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1220)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1221)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1222)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1223)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1224)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1228)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1229)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1230)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1228)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1229)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1230)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1231)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1228)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1229)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1230)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1231)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1232)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1233)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1237)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1238)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1239)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1237)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1238)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1239)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1240)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1237)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1238)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1239)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1240)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*9) + 1241)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + 143)]))
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*784) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
- }
+ compute[((blockIdx.x*1568) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
+ compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
</pre></div>
@@ -725,7 +1676,7 @@ 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: 0.216 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.217 ms
</pre></div>
</div>
</div>
@@ -756,35 +1707,35 @@ 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=1)
-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_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
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=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=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=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=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+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=7)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_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=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
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=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_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=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -803,14 +1754,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+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=224)
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=1)
+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=24)
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=112)
+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=224)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -828,10 +1779,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[3072];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -839,125 +1790,1120 @@ extern "C" __global__ void __launch_bounds__(112) default_function_ker
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 112) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 224) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 336) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 448) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 560) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 672) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 896) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1120) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1232) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1344)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1344) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1456)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1456) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1680)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1680) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1792)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1904)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1904) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2016)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1560)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2128)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2128) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2240)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2240) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2464)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2464) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2576)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2576) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2688)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2688) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2800)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2800) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2912)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2912) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3024)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 2344)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3248)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3248) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3360)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3360) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3472)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3472) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3584)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3584) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3696)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3696) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3808)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3808) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1680) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1792) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1904) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2016) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2128) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2240) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2464) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2576) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2800) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2912) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3024) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 432)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 66)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 67)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 68)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 69)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + ((((int)threadIdx.x) % 7) * 9)) + 71)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[(((int)threadIdx.x) * 24)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && (((((int)threadIdx.x) * 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 1)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 2)] = (((((3 <= ((((int)threadIdx.x) * 8) % 27)) && ((((((int)threadIdx.x) * 24) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 8) / 27) * 49)) + ((((((int)threadIdx.x) * 8) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 3)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 4)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 5)] = (((((3 <= (((((int)threadIdx.x) * 8) + 1) % 27)) && ((((((int)threadIdx.x) * 24) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 6)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 7)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 8)] = (((((3 <= (((((int)threadIdx.x) * 8) + 2) % 27)) && ((((((int)threadIdx.x) * 24) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 24) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 12)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 13)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 14)] = (((((3 <= (((((int)threadIdx.x) * 8) + 4) % 27)) && ((((((int)threadIdx.x) * 24) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 4) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 15)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 16)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 17)] = (((((3 <= (((((int)threadIdx.x) * 8) + 5) % 27)) && ((((((int)threadIdx.x) * 24) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 5) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 18)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 19)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 20)] = (((((1 <= ((((((int)threadIdx.x) * 8) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 24) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 6) / 27) * 49)) + (((((((int)threadIdx.x) * 8) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 21)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 22)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 54) {
+ pad_temp_shared[((((int)threadIdx.x) * 24) + 23)] = (((((3 <= (((((int)threadIdx.x) * 8) + 7) % 27)) && ((((((int)threadIdx.x) * 24) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 8) + 7) / 27) * 49)) + (((((((int)threadIdx.x) * 8) + 7) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 128) {
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 165)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 166)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 167)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 168)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 169)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 170)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 174)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 175)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 176)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 177)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 178)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 179)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 183)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 184)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 185)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 186)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 187)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 188)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 246)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 247)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 248)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 249)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 250)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 251)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 336)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 337)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 338)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 339)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 340)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 341)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 345)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 346)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 347)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 348)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 349)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 350)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 408)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 409)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 410)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 411)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 412)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 413)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 417)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 418)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 419)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 420)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 421)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 422)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 426)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 427)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 428)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 429)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 430)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 431)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 489)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 490)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 491)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 492)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 493)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 494)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 498)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 499)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 500)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 501)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 502)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 503)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 588)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 589)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 590)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 591)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 592)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 593)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 655)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 651)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 652)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 653)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 654)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 655)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 656)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 657)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 660)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 661)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 662)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 663)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 658)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 660)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 661)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 662)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 663)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 664)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 659)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 660)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 661)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 662)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 663)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 664)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 665)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 666)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 669)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 670)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 671)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 672)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 667)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 669)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 670)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 671)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 672)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 673)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 668)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 669)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 670)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 671)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 672)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 673)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 674)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 729)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 732)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 733)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 734)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 735)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 730)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 732)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 733)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 734)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 735)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 736)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 731)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 732)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 733)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 734)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 735)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 736)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 737)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 738)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 741)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 742)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 743)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 744)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 739)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 741)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 742)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 743)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 744)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 745)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 740)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 741)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 742)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 743)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 744)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 745)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 746)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 747)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 750)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 751)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 752)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 753)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 748)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 750)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 751)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 752)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 753)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 754)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 749)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 750)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 751)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 752)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 753)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 754)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 755)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 810)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 813)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 814)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 815)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 816)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 811)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 813)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 814)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 815)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 816)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 817)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 812)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 813)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 814)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 815)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 816)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 817)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 818)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 907)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 903)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 904)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 905)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 906)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 907)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 908)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 909)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 912)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 913)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 914)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 915)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 910)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 912)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 913)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 914)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 915)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 916)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 911)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 912)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 913)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 914)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 915)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 916)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 917)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 972)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 975)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 976)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 977)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 978)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 973)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 975)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 976)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 977)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 978)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 979)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 974)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 975)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 976)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 977)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 978)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 979)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 980)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 981)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 984)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 985)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 986)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 987)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 982)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 984)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 985)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 986)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 987)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 988)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 983)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 984)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 985)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 986)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 987)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 988)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 989)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 990)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 993)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 994)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 995)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 996)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 991)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 993)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 994)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 995)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 996)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 997)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 992)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 993)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 994)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 995)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 996)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 997)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 998)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1053)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1056)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1057)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1058)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1059)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1056)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1057)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1058)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1059)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1060)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1056)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1057)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1058)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1059)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1060)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1061)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1062)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1065)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1066)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1067)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1068)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1065)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1066)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1067)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1068)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1069)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1065)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1066)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1067)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1068)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1069)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1070)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1074)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1075)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1076)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1077)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1079)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1147)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1149)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1150)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1151)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1156)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1157)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1158)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1156)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1157)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1158)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1159)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1156)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1157)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1158)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1159)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1160)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1219)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1220)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1221)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1219)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1220)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1221)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1222)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1219)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1220)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1221)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1222)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1223)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1224)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1228)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1229)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1230)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1228)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1229)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1230)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1231)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1228)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1229)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1230)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1231)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1232)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1233)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1237)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1238)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1239)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1237)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1238)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1239)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1240)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1237)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1238)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1239)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1240)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1241)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + 143)]));
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 784) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- }
+ compute[((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -993,7 +2939,7 @@ 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 40.678 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 29.614 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index b34c621189..52b7253868 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -902,7 +902,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.2542 8.2539 8.2554 8.2532 0.0009
+ 8.1955 8.2007 8.2013 8.1845 0.0078
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 206fdd3b2e..18ed28b170 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 746.2183 745.7884 747.5492 745.3171 0.9606
+ 755.1963 754.5660 756.6738 754.3492 1.0485
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ 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 29.211 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.247 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 ede0a14a8f..379897429f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,30 +625,80 @@ 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 = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 8) {
- for (i.inner.init: int32, 0, 2) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [256], [])[(((i.outer.inner*32) + (i.inner.init*16)) + j.init)] = 0f32
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 2) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*32) + (i.inner*16)) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*2048)) + (i.inner*256))
+ let cse_var_17: int32 = (cse_var_19 + 9)
+ let cse_var_16: int32 = (cse_var_19 + 8)
+ let cse_var_15: int32 = (cse_var_19 + 7)
+ let cse_var_14: int32 = (cse_var_19 + 6)
+ let cse_var_13: int32 = (cse_var_19 + 5)
+ let cse_var_12: int32 = (cse_var_19 + 4)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 2)
+ let cse_var_9: int32 = (cse_var_19 + 15)
+ let cse_var_8: int32 = (cse_var_19 + 14)
+ let cse_var_7: int32 = (cse_var_19 + 13)
+ let cse_var_6: int32 = (cse_var_19 + 12)
+ let cse_var_5: int32 = (cse_var_19 + 11)
+ let cse_var_4: int32 = (cse_var_19 + 10)
+ let cse_var_3: int32 = (cse_var_19 + 1)
+ {
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 64) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -686,7 +736,7 @@ 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: 2.189 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.838 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 608aaedaff..c0573eadc2 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">ΒΆ</a></h1>
-<p><strong>00:45.102</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:30.402</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,11 +336,11 @@
</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>00:45.065</p></td>
+<td><p>00:30.367</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>00:00.022</p></td>
+<td><p>00:00.020</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>
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 7388ae2686..558ec7ca3c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -557,9 +557,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 26.51/26.51 result: MeasureResult(costs=(0.0087316115,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.707612037658691, timestamp=1664264288.1242013) [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3500701
-No: 2 GFLOPS: 269.46/269.46 result: MeasureResult(costs=(0.000859136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.621802568435669, timestamp=1664264288.811587) [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5861275
-No: 3 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 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
@@ -681,8 +679,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7906761
-No: 4 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,593877
+No: 2 GFLOPS: 97.62/97.62 result: MeasureResult(costs=(0.002371547847826087,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1653003692626953, timestamp=1664273482.081091) [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7551857
+No: 3 GFLOPS: 40.70/97.62 result: MeasureResult(costs=(0.005688332444444445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.5143184661865234, timestamp=1664273483.8374388) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8923280
+No: 4 GFLOPS: 0.00/97.62 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
@@ -804,8 +804,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9432430
-No: 5 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8412681
+No: 5 GFLOPS: 0.00/97.62 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
@@ -927,8 +927,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9391826
-No: 6 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6672635
+No: 6 GFLOPS: 0.00/97.62 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
@@ -1050,10 +1050,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1370925
-No: 7 GFLOPS: 211.65/269.46 result: MeasureResult(costs=(0.0010937779387755102,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4072532653808594, timestamp=1664264294.042101) [('tile_f', [-1, 1, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2559794
-No: 8 GFLOPS: 30.92/269.46 result: MeasureResult(costs=(0.007486210357142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4876489639282227, timestamp=1664264294.7134411) [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8330604
-No: 9 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6613456
+No: 7 GFLOPS: 35.33/97.62 result: MeasureResult(costs=(0.006553338411764705,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4227442741394043, timestamp=1664273487.6779063) [('tile_f', [-1, 16, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5887424
+No: 8 GFLOPS: 0.00/97.62 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
@@ -1175,9 +1174,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7934894
-No: 10 GFLOPS: 5.93/269.46 result: MeasureResult(costs=(0.039066184749999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.5282135009765625, timestamp=1664264302.4238741) [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8341500
-No: 11 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3663876
+No: 9 GFLOPS: 5.20/97.62 result: MeasureResult(costs=(0.0445004805,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2675786018371582, timestamp=1664273489.5801508) [('tile_f', [-1, 4, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,605542
+No: 10 GFLOPS: 0.00/97.62 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
@@ -1299,8 +1298,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7884556
-No: 12 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10025409
+No: 11 GFLOPS: 0.00/97.62 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
@@ -1422,8 +1421,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7769621
-No: 13 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7341565
+No: 12 GFLOPS: 78.43/97.62 result: MeasureResult(costs=(0.0029518690545454547,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7027909755706787, timestamp=1664273490.5161994) [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4295417
+No: 13 GFLOPS: 0.00/97.62 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
@@ -1545,8 +1545,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3504569
-No: 14 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9868006
+No: 14 GFLOPS: 0.00/97.62 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
@@ -1668,8 +1668,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 1, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6923396
-No: 15 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1461908
+No: 15 GFLOPS: 0.00/97.62 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
@@ -1791,8 +1791,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3431971
-No: 16 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8104269
+No: 16 GFLOPS: 0.00/97.62 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
@@ -1914,8 +1914,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2737510
-No: 17 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6575292
+No: 17 GFLOPS: 23.68/97.62 result: MeasureResult(costs=(0.009774371,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2793161869049072, timestamp=1664273492.161263) [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6790136
+No: 18 GFLOPS: 236.64/236.64 result: MeasureResult(costs=(0.000978286187878788,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3463761806488037, timestamp=1664273493.0877633) [('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,405495
+No: 19 GFLOPS: 0.00/236.64 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
@@ -2037,8 +2039,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 2, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8053816
-No: 18 GFLOPS: 0.00/269.46 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2044362
+No: 20 GFLOPS: 0.00/236.64 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
@@ -2160,131 +2162,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
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, 512, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5277149
-No: 19 GFLOPS: 0.00/269.46 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 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)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- 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
-
-Traceback (most recent call last):
- 24: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 22: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 21: operator()
- at ../include/tvm/runtime/packed_func.h:1731
- 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
- at ../include/tvm/runtime/packed_func.h:1671
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1631
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1631
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1646
- 13: operator()
- at ../src/driver/driver_api.cc:379
- 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
- at ../src/driver/driver_api.cc:365
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:260
- 10: tvm::transform::Pass::operator()(tvm::IRModule) const
- at ../src/ir/transform.cc:258
- 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:453
- 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/ir/transform.cc:274
- 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
- at ../src/tir/ir/transform.cc:100
- 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
- at ../include/tvm/runtime/packed_func.h:1750
- 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
- at ../include/tvm/runtime/packed_func.h:1694
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
- at ../include/tvm/runtime/packed_func.h:1618
- 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 1: Call
- at ../include/tvm/runtime/packed_func.h:1213
- 0: operator()
- at ../src/runtime/c_runtime_api.cc:534
- File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1220402
-No: 20 GFLOPS: 60.89/269.46 result: MeasureResult(costs=(0.003802074,), error_no=MeasureErrorNo.NO_ERROR, all_cost=10.675763130187988, timestamp=1664264313.508275) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8062186
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3886463
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2323,9 +2201,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5861275
+[('tile_f', [-1, 2, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,405495
Finish loading 20 records
-Time cost of this operator: 0.001235
+Time cost of this operator: 0.001389
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index e9cb5d6da1..1d436d0b16 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -582,10 +582,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.3 98.702 (1, 2, 10, 10, 3) 2 1 [311.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.13 0.992 (1, 6, 10, 10) 1 1 [3.13]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.305 (1, 1, 10, 10, 3) 1 1 [0.963]
-Total_time - 315.393 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.1 98.743 (1, 2, 10, 10, 3) 2 1 [316.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.049 0.952 (1, 6, 10, 10) 1 1 [3.049]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.974 0.304 (1, 1, 10, 10, 3) 1 1 [0.974]
+Total_time - 320.123 - - - - -
</pre></div>
</div>
</div>
@@ -636,10 +636,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## 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 100.1 97.364 (1, 6, 10, 10, 1) 2 1 [100.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.703 (1, 6, 10, 10) 1 1 [1.75]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.933 (1, 1, 10, 10, 3) 1 1 [0.96]
-Total_time - 102.81 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.5 97.462 (1, 6, 10, 10, 1) 2 1 [102.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.822 1.733 (1, 6, 10, 10) 1 1 [1.822]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.847 0.805 (1, 3, 10, 10, 1) 1 1 [0.847]
+Total_time - 105.169 - - - - -
</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 fdc0b5950e..c6b4b2bb2c 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/tmpu3e79fd5/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpffx_fugf/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="[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], [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/tmpu3e79fd5/images/target contains 8144 images
-/tmp/tmpu3e79fd5/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [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/tmpffx_fugf/images/target contains 8144 images
+/tmp/tmpffx_fugf/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 - 46s - loss: 0.2115 - accuracy: 0.9254 - val_loss: 0.1110 - val_accuracy: 0.9607 - 46s/epoch - 141ms/step
+328/328 - 47s - loss: 0.2181 - accuracy: 0.9239 - val_loss: 0.1244 - val_accuracy: 0.9653 - 47s/epoch - 142ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.0983 - accuracy: 0.9639 - val_loss: 0.0959 - val_accuracy: 0.9664 - 43s/epoch - 131ms/step
+328/328 - 43s - loss: 0.1013 - accuracy: 0.9617 - val_loss: 0.1932 - val_accuracy: 0.9400 - 43s/epoch - 132ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0638 - accuracy: 0.9761 - val_loss: 0.1963 - val_accuracy: 0.9396 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0657 - accuracy: 0.9757 - val_loss: 0.1148 - val_accuracy: 0.9619 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7f8d38fc1510>
+<keras.callbacks.History object at 0x7f87df6f59d0>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVMβs autotuning capabilities</a> to dramatically improve the modelβs performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 35.116 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 38.337 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 2e2c81112c..494f5119e4 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">ΒΆ</a></h1>
-<p><strong>05:43.748</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:47.013</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>04:35.116</p></td>
+<td><p>04:38.337</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>00:55.236</p></td>
+<td><p>00:55.346</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>00:09.352</p></td>
+<td><p>00:09.245</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>00:04.041</p></td>
+<td><p>00:04.083</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 a659fe63a9..bce16f6ee9 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">ΒΆ</a></h1>
-<p><strong>00:43.299</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.084</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>00:31.740</p></td>
+<td><p>00:31.757</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.053</p></td>
+<td><p>00:09.870</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>00:01.500</p></td>
+<td><p>00:01.450</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 84990c49f9..1373ed359a 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 0x7f8d35f56950>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f87e5cfc830>
</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 6bb8f8ad63..7500984bc5 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">ΒΆ</a></h1>
-<p><strong>00:07.854</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.751</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:05.589</p></td>
+<td><p>00:05.425</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>00:01.000</p></td>
+<td><p>00:01.013</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>00:00.547</p></td>
+<td><p>00:00.569</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>00:00.526</p></td>
+<td><p>00:00.551</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>00:00.112</p></td>
+<td><p>00:00.113</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>00:00.039</p></td>
+<td><p>00:00.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 1a0bab6e17..f342efac8b 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/tmp3q6u3ki5/input0.cc'\nsource_filename = \"/tmp/tmp3q6u3ki5/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/tmp48ppcfty/input0.cc'\nsource_filename = \"/tmp/tmp48ppcfty/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/doxygen/namespacemembers_func_m.html b/docs/reference/api/doxygen/namespacemembers_func_m.html
index 70b72d9384..dbd2fa308a 100644
--- a/docs/reference/api/doxygen/namespacemembers_func_m.html
+++ b/docs/reference/api/doxygen/namespacemembers_func_m.html
@@ -89,7 +89,7 @@ $(function() {
: <a class="el" href="namespacetvm_1_1topi_1_1x86.html#a7740a46043b6c5514806684970e215b2">tvm::topi::x86</a>
</li>
<li>MakePackedAPI()
-: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7">tvm::tir::transform</a>
+: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec">tvm::tir::transform</a>
</li>
<li>MakeReduceAxes()
: <a class="el" href="namespacetvm_1_1topi.html#a86c0ad6fe6717f649f3fba88a3dc4b29">tvm::topi</a>
diff --git a/docs/reference/api/doxygen/namespacemembers_m.html b/docs/reference/api/doxygen/namespacemembers_m.html
index 4409991d25..14698cec21 100644
--- a/docs/reference/api/doxygen/namespacemembers_m.html
+++ b/docs/reference/api/doxygen/namespacemembers_m.html
@@ -89,7 +89,7 @@ $(function() {
: <a class="el" href="namespacetvm_1_1topi_1_1x86.html#a7740a46043b6c5514806684970e215b2">tvm::topi::x86</a>
</li>
<li>MakePackedAPI()
-: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7">tvm::tir::transform</a>
+: <a class="el" href="namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec">tvm::tir::transform</a>
</li>
<li>MakeReduceAxes()
: <a class="el" href="namespacetvm_1_1topi.html#a86c0ad6fe6717f649f3fba88a3dc4b29">tvm::topi</a>
diff --git a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html
index 0cecf09855..f34c9fe55a 100644
--- a/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html
+++ b/docs/reference/api/doxygen/namespacetvm_1_1tir_1_1transform.html
@@ -130,9 +130,9 @@ Functions</h2></td></tr>
<tr class="memitem:a8c492c5e21f3cd636bc27493153dcbbe"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a8c492c5e21f3cd636bc27493153dcbbe">InstrumentBoundCheckers</a> ()</td></tr>
<tr class="memdesc:a8c492c5e21f3cd636bc27493153dcbbe"><td class="mdescLeft"> </td><td class="mdescRight">Instruments bound checkers. <a href="#a8c492c5e21f3cd636bc27493153dcbbe">More...</a><br /></td></tr>
<tr class="separator:a8c492c5e21f3cd636bc27493153dcbbe"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:abaf9c953f28d23408872beef5aa33af7"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7">MakePackedAPI</a> (int num_unpacked_args)</td></tr>
-<tr class="memdesc:abaf9c953f28d23408872beef5aa33af7"><td class="mdescLeft"> </td><td class="mdescRight">Transform the high-level <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to a low-level version that can be used as an API function. <a href="#abaf9c953f28d23408872beef5aa33af7">More...</a><br /></td></tr>
-<tr class="separator:abaf9c953f28d23408872beef5aa33af7"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a38be3df8947fea34192c61bfed1c6eec"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec">MakePackedAPI</a> ()</td></tr>
+<tr class="memdesc:a38be3df8947fea34192c61bfed1c6eec"><td class="mdescLeft"> </td><td class="mdescRight">Transform the high-level <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to a low-level version that can be used as an API function. <a href="#a38be3df8947fea34192c61bfed1c6eec">More...</a><br /></td></tr>
+<tr class="separator:a38be3df8947fea34192c61bfed1c6eec"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a1903620176fa71b005fd7c58656d7139"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a1903620176fa71b005fd7c58656d7139">MakeUnpackedAPI</a> ()</td></tr>
<tr class="memdesc:a1903620176fa71b005fd7c58656d7139"><td class="mdescLeft"> </td><td class="mdescRight">Transform the high-level <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to a C signature that can be used to call the operator directly. <a href="#a1903620176fa71b005fd7c58656d7139">More...</a><br /></td></tr>
<tr class="separator:a1903620176fa71b005fd7c58656d7139"><td class="memSeparator" colspan="2"> </td></tr>
@@ -1141,8 +1141,8 @@ Functions</h2></td></tr>
</div>
</div>
-<a id="abaf9c953f28d23408872beef5aa33af7"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#abaf9c953f28d23408872beef5aa33af7">◆ </a></span>MakePackedAPI()</h2>
+<a id="a38be3df8947fea34192c61bfed1c6eec"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a38be3df8947fea34192c61bfed1c6eec">◆ </a></span>MakePackedAPI()</h2>
<div class="memitem">
<div class="memproto">
@@ -1150,8 +1150,7 @@ Functions</h2></td></tr>
<tr>
<td class="memname"><a class="el" href="classtvm_1_1transform_1_1Pass.html">Pass</a> tvm::tir::transform::MakePackedAPI </td>
<td>(</td>
- <td class="paramtype">int </td>
- <td class="paramname"><em>num_unpacked_args</em></td><td>)</td>
+ <td class="paramname"></td><td>)</td>
<td></td>
</tr>
</table>
@@ -1162,15 +1161,9 @@ Functions</h2></td></tr>
<li>Map the values in the api_args to <a class="el" href="classtvm_1_1tir_1_1Var.html" title="a named variable in TIR ">Var</a> that is required by body.</li>
<li>Insert assertions to check type/value of the passed arguments.</li>
</ul>
-<dl class="params"><dt>Parameters</dt><dd>
- <table class="params">
- <tr><td class="paramname">num_unpacked_args</td><td>Number of arguments that are processed in plain form instead of packed form.</td></tr>
- </table>
- </dd>
-</dl>
<dl class="section note"><dt>Note</dt><dd>The function signature have two cases</dd></dl>
-<p>let num_packed_args = len(api_args) - num_unpacked_args;</p>
-<p>if num_packed_args is zero: f(api_arg_0, api_arg_1, .., api_arg_n) where n == len(api_args)</p>
+<p>let num_packed_args = len(api_args);</p>
+<p>if num_packed_args is zero: f()</p>
<p>if num_packed_args is not zero: f(TVMArg* packed_args, int* packed_arg_type_ids, int num_packed_args, api_arg_k, api_arg_k+1, ... api_arg_n, TVMValue* out_ret_val, int* out_ret_tcode)</p>
<p>where n == len(api_args), k == num_packed_args</p>
<dl class="section return"><dt>Returns</dt><dd>The pass. </dd></dl>
diff --git a/docs/reference/api/doxygen/search/all_e.js b/docs/reference/api/doxygen/search/all_e.js
index b0977fa52b..b5568ee315 100644
--- a/docs/reference/api/doxygen/search/all_e.js
+++ b/docs/reference/api/doxygen/search/all_e.js
@@ -11,7 +11,7 @@ var searchData=
['makecommreducer',['MakeCommReducer',['../namespacetvm_1_1topi.html#a1d3988f52c26cc29967cefa057b79372',1,'tvm::topi']]],
['makeconstscalar',['MakeConstScalar',['../namespacetvm_1_1tir.html#a0db485654cd60d43962f532a1b16026c',1,'tvm::tir::MakeConstScalar(DataType t, ValueType value, Span span=Span())'],['../namespacetvm_1_1tir.html#a79fc1666a383e629654ca5f8d2cdf9f4',1,'tvm::tir::MakeConstScalar(DataType t, bool value, Span span)']]],
['makedefaultschedule',['MakeDefaultSchedule',['../namespacetvm_1_1topi_1_1x86.html#a7740a46043b6c5514806684970e215b2',1,'tvm::topi::x86']]],
- ['makepackedapi',['MakePackedAPI',['../namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7',1,'tvm::tir::transform']]],
+ ['makepackedapi',['MakePackedAPI',['../namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec',1,'tvm::tir::transform']]],
['makereduceaxes',['MakeReduceAxes',['../namespacetvm_1_1topi.html#a86c0ad6fe6717f649f3fba88a3dc4b29',1,'tvm::topi']]],
['makereducetargetshape',['MakeReduceTargetShape',['../namespacetvm_1_1topi.html#ad58b3ba5122294bd1eb045b5792c3976',1,'tvm::topi']]],
['makeslice',['MakeSlice',['../classtvm_1_1tir_1_1Buffer.html#a9c3841e4217f94824df6e92a785655d5',1,'tvm::tir::Buffer']]],
diff --git a/docs/reference/api/doxygen/search/functions_d.js b/docs/reference/api/doxygen/search/functions_d.js
index 4aecb7b693..c62c0111db 100644
--- a/docs/reference/api/doxygen/search/functions_d.js
+++ b/docs/reference/api/doxygen/search/functions_d.js
@@ -11,7 +11,7 @@ var searchData=
['makecommreducer',['MakeCommReducer',['../namespacetvm_1_1topi.html#a1d3988f52c26cc29967cefa057b79372',1,'tvm::topi']]],
['makeconstscalar',['MakeConstScalar',['../namespacetvm_1_1tir.html#a0db485654cd60d43962f532a1b16026c',1,'tvm::tir::MakeConstScalar(DataType t, ValueType value, Span span=Span())'],['../namespacetvm_1_1tir.html#a79fc1666a383e629654ca5f8d2cdf9f4',1,'tvm::tir::MakeConstScalar(DataType t, bool value, Span span)']]],
['makedefaultschedule',['MakeDefaultSchedule',['../namespacetvm_1_1topi_1_1x86.html#a7740a46043b6c5514806684970e215b2',1,'tvm::topi::x86']]],
- ['makepackedapi',['MakePackedAPI',['../namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7',1,'tvm::tir::transform']]],
+ ['makepackedapi',['MakePackedAPI',['../namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec',1,'tvm::tir::transform']]],
['makereduceaxes',['MakeReduceAxes',['../namespacetvm_1_1topi.html#a86c0ad6fe6717f649f3fba88a3dc4b29',1,'tvm::topi']]],
['makereducetargetshape',['MakeReduceTargetShape',['../namespacetvm_1_1topi.html#ad58b3ba5122294bd1eb045b5792c3976',1,'tvm::topi']]],
['makeslice',['MakeSlice',['../classtvm_1_1tir_1_1Buffer.html#a9c3841e4217f94824df6e92a785655d5',1,'tvm::tir::Buffer']]],
diff --git a/docs/reference/api/doxygen/tir_2transform_8h.html b/docs/reference/api/doxygen/tir_2transform_8h.html
index c25e1e2171..7142208816 100644
--- a/docs/reference/api/doxygen/tir_2transform_8h.html
+++ b/docs/reference/api/doxygen/tir_2transform_8h.html
@@ -146,9 +146,9 @@ Functions</h2></td></tr>
<tr class="memitem:a8c492c5e21f3cd636bc27493153dcbbe"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a8c492c5e21f3cd636bc27493153dcbbe">tvm::tir::transform::InstrumentBoundCheckers</a> ()</td></tr>
<tr class="memdesc:a8c492c5e21f3cd636bc27493153dcbbe"><td class="mdescLeft"> </td><td class="mdescRight">Instruments bound checkers. <a href="namespacetvm_1_1tir_1_1transform.html#a8c492c5e21f3cd636bc27493153dcbbe">More...</a><br /></td></tr>
<tr class="separator:a8c492c5e21f3cd636bc27493153dcbbe"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:abaf9c953f28d23408872beef5aa33af7"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7">tvm::tir::transform::MakePackedAPI</a> (int num_unpacked_args)</td></tr>
-<tr class="memdesc:abaf9c953f28d23408872beef5aa33af7"><td class="mdescLeft"> </td><td class="mdescRight">Transform the high-level <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to a low-level version that can be used as an API function. <a href="namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7">More...</a><br /></td></tr>
-<tr class="separator:abaf9c953f28d23408872beef5aa33af7"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a38be3df8947fea34192c61bfed1c6eec"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec">tvm::tir::transform::MakePackedAPI</a> ()</td></tr>
+<tr class="memdesc:a38be3df8947fea34192c61bfed1c6eec"><td class="mdescLeft"> </td><td class="mdescRight">Transform the high-level <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to a low-level version that can be used as an API function. <a href="namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec">More...</a><br /></td></tr>
+<tr class="separator:a38be3df8947fea34192c61bfed1c6eec"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a1903620176fa71b005fd7c58656d7139"><td class="memItemLeft" align="right" valign="top">Pass </td><td class="memItemRight" valign="bottom"><a class="el" href="namespacetvm_1_1tir_1_1transform.html#a1903620176fa71b005fd7c58656d7139">tvm::tir::transform::MakeUnpackedAPI</a> ()</td></tr>
<tr class="memdesc:a1903620176fa71b005fd7c58656d7139"><td class="mdescLeft"> </td><td class="mdescRight">Transform the high-level <a class="el" href="classtvm_1_1tir_1_1PrimFunc.html" title="Managed reference to PrimFuncNode. ">PrimFunc</a> to a C signature that can be used to call the operator directly. <a href="namespacetvm_1_1tir_1_1transform.html#a1903620176fa71b005fd7c58656d7139">More...</a><br /></td></tr>
<tr class="separator:a1903620176fa71b005fd7c58656d7139"><td class="memSeparator" colspan="2"> </td></tr>
diff --git a/docs/reference/api/doxygen/tir_2transform_8h_source.html b/docs/reference/api/doxygen/tir_2transform_8h_source.html
index 1696d89821..f391544d98 100644
--- a/docs/reference/api/doxygen/tir_2transform_8h_source.html
+++ b/docs/reference/api/doxygen/tir_2transform_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">transform.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="tir_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or m [...]
+<a href="tir_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or m [...]
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a0979c9d3bf0e64205f16aa00d331c6b5"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a0979c9d3bf0e64205f16aa00d331c6b5">tvm::tir::transform::LowerIntrin</a></div><div class="ttdeci">Pass LowerIntrin()</div><div class="ttdoc">Lower the target specific function intrinsics in each of the function. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_ae10fc2ab38a0cdfe79cb7f718549f532"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#ae10fc2ab38a0cdfe79cb7f718549f532">tvm::tir::transform::InferFragment</a></div><div class="ttdeci">Pass InferFragment()</div><div class="ttdoc">Infer the TensorCore fragment infomation using tensor intrinsics. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a778d3e1efecdff97e7bcf0e6a5406e61"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a778d3e1efecdff97e7bcf0e6a5406e61">tvm::tir::transform::StorageFlatten</a></div><div class="ttdeci">Pass StorageFlatten(int cache_line_size, bool create_bound_attribute=false)</div><div class="ttdoc">Flatten the multi-dimensional read/write to single dimensional Load/Store. </div></div>
@@ -84,12 +84,12 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_af2cdafede0174363f10db49d9a61fbe3"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#af2cdafede0174363f10db49d9a61fbe3">tvm::tir::transform::ManifestSharedMemoryLocalStage</a></div><div class="ttdeci">Pass ManifestSharedMemoryLocalStage()</div><div class="ttdoc">Add the explicit local stage for the shared memory access on GPU. </div></div>
<div class="ttc" id="namespacetvm_1_1relay_1_1transform_html_a3ae923037d22b4640b450c06e6c1e33e"><div class="ttname"><a href="namespacetvm_1_1relay_1_1transform.html#a3ae923037d22b4640b450c06e6c1e33e">tvm::relay::transform::Sequential</a></div><div class="ttdeci">tvm::transform::Sequential Sequential</div><div class="ttdef"><b>Definition:</b> transform.h:49</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_acd2b8fdd84785388630e2d52a6e3cc54"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#acd2b8fdd84785388630e2d52a6e3cc54">tvm::tir::transform::HoistIfThenElse</a></div><div class="ttdeci">Pass HoistIfThenElse()</div><div class="ttdoc">Hoist loop-invariant IfThenElse nodes to outside the elligible loops. </div></div>
-<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_abaf9c953f28d23408872beef5aa33af7"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#abaf9c953f28d23408872beef5aa33af7">tvm::tir::transform::MakePackedAPI</a></div><div class="ttdeci">Pass MakePackedAPI(int num_unpacked_args)</div><div class="ttdoc">Transform the high-level PrimFunc to a low-level version that can be used as an API function...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_aa97b7253e13e662adc5f9ad3367746a8"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#aa97b7253e13e662adc5f9ad3367746a8">tvm::tir::transform::NarrowDataType</a></div><div class="ttdeci">Pass NarrowDataType(int target_bits)</div><div class="ttdoc">Narrow down PrimExpr datatype in stmt to target_bits. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a641a33aa6ac3ec146be1196a091af5d5"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a641a33aa6ac3ec146be1196a091af5d5">tvm::tir::transform::LowerCrossThreadReduction</a></div><div class="ttdeci">Pass LowerCrossThreadReduction()</div><div class="ttdoc">Lower cross-thread reduction from thread bindings to intrinsic function calls. </div></div>
<div class="ttc" id="namespacetvm_1_1script_1_1ir__builder_1_1tir_html_a713fe9c5ed9b44e16b7e5f9a23622543"><div class="ttname"><a href="namespacetvm_1_1script_1_1ir__builder_1_1tir.html#a713fe9c5ed9b44e16b7e5f9a23622543">tvm::script::ir_builder::tir::PrimFunc</a></div><div class="ttdeci">PrimFuncFrame PrimFunc()</div><div class="ttdoc">The primitive function statement. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_ae70d9af70526908167101609baaf4142"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#ae70d9af70526908167101609baaf4142">tvm::tir::transform::InjectCopyIntrin</a></div><div class="ttdeci">Pass InjectCopyIntrin(String pragma_key, runtime::PackedFunc fintrin)</div><div class="ttdoc">Inject copy intrinsics with optional pad. </div></div>
<div class="ttc" id="tir_2function_8h_html"><div class="ttname"><a href="tir_2function_8h.html">function.h</a></div><div class="ttdoc">TIR Function. </div></div>
+<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a38be3df8947fea34192c61bfed1c6eec"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a38be3df8947fea34192c61bfed1c6eec">tvm::tir::transform::MakePackedAPI</a></div><div class="ttdeci">Pass MakePackedAPI()</div><div class="ttdoc">Transform the high-level PrimFunc to a low-level version that can be used as an API function...</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_a17b0910c03b6f2d462448fa2725c1f5e"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#a17b0910c03b6f2d462448fa2725c1f5e">tvm::tir::transform::LoopPartition</a></div><div class="ttdeci">Pass LoopPartition()</div><div class="ttdoc">partition loops in the stmt. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_ae976049e464f05cbd3ddfdbfcf8cd1d6"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#ae976049e464f05cbd3ddfdbfcf8cd1d6">tvm::tir::transform::BindTarget</a></div><div class="ttdeci">Pass BindTarget(Target target)</div><div class="ttdoc">Annotate a PrimFunc with a given target. </div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1transform_html_ae14f476f006bd24ef62f7c170aded18d"><div class="ttname"><a href="namespacetvm_1_1tir_1_1transform.html#ae14f476f006bd24ef62f7c170aded18d">tvm::tir::transform::ConvertBlocksToOpaque</a></div><div class="ttdeci">Pass ConvertBlocksToOpaque()</div><div class="ttdoc">Substitute all the block vars with the PrimExprs they are bound to, indicated by the corresponding it...</div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 11a059bcc8..8e8e51038d 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/tir.html b/docs/reference/api/python/tir.html
index 72709b42db..838b012262 100644
--- a/docs/reference/api/python/tir.html
+++ b/docs/reference/api/python/tir.html
@@ -7908,7 +7908,7 @@ reduction.</p>
<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.LowerWarpMemory" title="tvm.tir.transform.LowerWarpMemory"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LowerWarpMemory</span></code></a>()</p></td>
<td><p>Lower warp memory access to low-level device related function calls.</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.MakePackedAPI" title="tvm.tir.transform.MakePackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakePackedAPI</span></code></a>([num_unpacked_params])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="#tvm.tir.transform.MakePackedAPI" title="tvm.tir.transform.MakePackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakePackedAPI</span></code></a>()</p></td>
<td><p>Transform the PrimFuncs in the module to a packed func API.</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="#tvm.tir.transform.MakeUnpackedAPI" title="tvm.tir.transform.MakeUnpackedAPI"><code class="xref py py-obj docutils literal notranslate"><span class="pre">MakeUnpackedAPI</span></code></a>()</p></td>
@@ -8871,19 +8871,14 @@ intrinsic function calls.</p>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.tir.transform.MakePackedAPI">
-<span class="sig-prename descclassname"><span class="pre">tvm.tir.transform.</span></span><span class="sig-name descname"><span class="pre">MakePackedAPI</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_unpacked_params</span></span><span class="p"><span class="pre">:</span></span> <span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><span class="pre">int< [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.tir.transform.</span></span><span class="sig-name descname"><span class="pre">MakePackedAPI</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#tvm.tir.transform.MakePackedAPI" title="Permalink to this definition">ΒΆ</a></dt>
<dd><p>Transform the PrimFuncs in the module to a packed func API.</p>
<dl class="field-list simple">
-<dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>num_unpacked_params</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.10)"><em>int</em></a>) β Number of parameters that we hope to directly pass via normal arguments
-following the PackedFunc input signature. If it is specified as -1 or it
-is less than the number of arguments, the pass will packed arguments still.</p>
-</dd>
-<dt class="field-even">Returns</dt>
-<dd class="field-even"><p><strong>fpass</strong> β The result pass</p>
+<dt class="field-odd">Returns</dt>
+<dd class="field-odd"><p><strong>fpass</strong> β The result pass</p>
</dd>
-<dt class="field-odd">Return type</dt>
-<dd class="field-odd"><p><a class="reference internal" href="ir.html#tvm.transform.Pass" title="tvm.transform.Pass">tvm.transform.Pass</a></p>
+<dt class="field-even">Return type</dt>
+<dd class="field-even"><p><a class="reference internal" href="ir.html#tvm.transform.Pass" title="tvm.transform.Pass">tvm.transform.Pass</a></p>
</dd>
</dl>
</dd></dl>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 314601dd77..b83a35b10a 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/b61f633e1/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 5660c54a95..bc7a839d10 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/b61f633e1/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 b7538b36a4..68b19988a0 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/b61f633e1/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 c75f1556c8..a54f916049 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/b61f633e1/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 ce19bc11ee..1feefbc277 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/b61f633e1/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 e705784a18..53f5f70c61 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/b61f633e1/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 1b96d79888..4d9a02aba9 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/b61f633e1/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 cd2a19f5de..c71bae66dd 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/b61f633e1/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/web/src/runtime.ts#L1145">runtime.ts:1145</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/b61f633e1/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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 a2ac6fd22f..0044bd0aec 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/b61f633e1/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/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/b61f633e1/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/7a4c10c44/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
... 2104 lines suppressed ...