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 2023/01/04 21:56:47 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@116453f5cfc51e4682589b8e30bc87e738e44556)
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 65d018c0c9 deploying docs (apache/tvm@116453f5cfc51e4682589b8e30bc87e738e44556)
65d018c0c9 is described below
commit 65d018c0c97cfc2cc3f54c1b2a46160e0a6d31dc
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jan 4 21:56:39 2023 +0000
deploying docs (apache/tvm@116453f5cfc51e4682589b8e30bc87e738e44556)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 332190 -> 325223 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23824 -> 23705 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_adreno.rst.txt | 2 +-
.../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 | 10 +-
.../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 | 3409 +++++---------------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 22 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 200 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../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 | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../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 | 11 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 34 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
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 | 10 +-
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 | 3409 +++++---------------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 22 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 200 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../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 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 274 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
130 files changed, 2697 insertions(+), 6178 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index aaa507d64d..1bd01f9438 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 5ff98f857f..b19cc4a2f9 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 2ce6839a92..262ec5d5c8 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 9.048 seconds)
+ **Total running time of the script:** ( 1 minutes 8.908 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 9e9654abd0..d3007248dd 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 930ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 939ms/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 3503019bb3..16da07f317 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.zipcd5cfa5d-5860-4fdf-8e3a-c90ec05901d1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip8e39e356-cb66-478a-a46c-4a137e0df0d7 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 843ec5fdd4..052ccdcb98 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]
20%|#9 | 8.12M/41.5M [00:00<00:00, 84.6MB/s]
39%|###9 | 16.2M/41.5M [00:00<00:00, 71.7MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 66.4MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 92.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 85.0MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 52.8MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 52.7MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 53.6MB/s]
75%|#######5 | 31.2M/41.5M [00:00<00:00, 66.0MB/s]
91%|#########1| 37.8M/41.5M [00:00<00:00, 46.3MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 51.1MB/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 c0c3b94e6c..2ab3501b03 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
22%|##2 | 9.98M/44.7M [00:00<00:00, 105MB/s]
52%|#####2 | 23.3M/44.7M [00:00<00:00, 125MB/s]
79%|#######8 | 35.2M/44.7M [00:00<00:00, 112MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
28%|##7 | 12.4M/44.7M [00:00<00:00, 130MB/s]
56%|#####5 | 24.8M/44.7M [00:00<00:00, 111MB/s]
80%|#######9 | 35.5M/44.7M [00:00<00:00, 106MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 66228fb1fe..4dc6d9be47 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 11.097 seconds)
+ **Total running time of the script:** ( 1 minutes 11.600 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 9495ffd13f..9ac76980db 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
=================
-**05:38.551** total execution time for **how_to_compile_models** files:
+**05:40.675** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.097 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:11.600 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:09.048 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:08.908 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.831 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:46.877 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.372 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.324 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.454 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.704 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:26.121 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.834 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.052 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.947 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.330 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.201 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.886 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.395 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 29c6077529..f9bbdd0190 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2544.7204 2544.3257 2547.5219 2542.4330 1.6902
+ 2754.8814 2754.7721 2757.5498 2753.2221 1.3234
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 40538f1312..bb624c2c2e 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
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6435 15.6362 15.7886 15.5259 0.0888
+ 16.9005 16.8900 17.9896 15.7231 0.5978
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 7c3d2a9083..eaeb6cfdc6 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
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
5%|4 | 8.02M/170M [00:00<00:02, 84.1MB/s]
13%|#2 | 21.5M/170M [00:00<00:01, 118MB/s]
19%|#9 | 32.7M/170M [00:00<00:01, 114MB/s]
26%|##5 | 43.6M/170M [00:00<00:01, 113MB/s]
32%|###2 | 54.5M/170M [00:00<00:01, 114MB/s]
38%|###8 | 65.4M/170M [00:00<00:01, 108MB/s]
45%|####4 | 75.7M/170M [00:00<00:00, 106MB/s]
51%|##### | 85.8M/170M [00:00<00:00, 104MB/s]
56%|#####6 | 95.8M/170M [00:00<00:00, 103MB/s]
62%|######2 | 106M/170M [00:01<00:00, 93.8MB/s]
68%|######7 | 115M/170M [00:01<00:00, 93.2MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 106MB/s]
81%|########1 | 138M/170M [00:01<00:00, 98.4MB/s]
88%|########8 | 150M/170M [00:01<00:00, 105MB/s]
94%|#########4| 160M/170M [00:01<00:00, 103MB/s]
100%|#########9| 170M/170M [00:01<00:00, 102MB/s]
100%|##########| 170M/170M [00:01<00:00, 103MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
8%|7 | 12.9M/170M [00:00<00:01, 135MB/s]
15%|#5 | 25.8M/170M [00:00<00:01, 91.7MB/s]
24%|##3 | 40.5M/170M [00:00<00:01, 114MB/s]
31%|### | 52.4M/170M [00:00<00:01, 109MB/s]
37%|###7 | 63.3M/170M [00:00<00:01, 110MB/s]
44%|####3 | 74.2M/170M [00:00<00:01, 95.0MB/s]
52%|#####1 | 87.6M/170M [00:00<00:00, 107MB/s]
58%|#####7 | 98.5M/170M [00:01<00:00, 98.8MB/s]
65%|######4 | 110M/170M [00:01<00:00, 106MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 98.3MB/s]
78%|#######8 | 133M/170M [00:01<00:00, 105MB/s]
84%|########4 | 143M/170M [00:01<00:00, 96.6MB/s]
90%|########9 | 152M/170M [00:01<00:00, 71.8MB/s]
96%|#########6| 164M/170M [00:01<00:00, 82.2MB/s]
100%|##########| 170M/170M [00:01<00:00, 96.2MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 12.882 seconds)
+ **Total running time of the script:** ( 3 minutes 11.144 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 723c733c4f..b3e8400f1b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
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]
68%|######8 | 9.27M/13.6M [00:00<00:00, 97.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 121MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 65.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 94.0MB/s]
@@ -418,7 +418,7 @@ 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)
- 90.3318 90.2340 94.1975 90.0638 0.4280
+ 90.1726 90.1287 91.4865 89.8042 0.2651
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.008 seconds)
+ **Total running time of the script:** ( 1 minutes 5.174 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 cf0417b59a..35c47c1205 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)
- 121.2613 121.2022 126.9510 120.4900 0.6470
+ 119.6057 119.6744 122.6713 117.5132 1.1431
@@ -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 30.667 seconds)
+ **Total running time of the script:** ( 2 minutes 28.138 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 5594cee3a0..432c757d5c 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 37.991 seconds)
+ **Total running time of the script:** ( 1 minutes 24.101 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 802e920128..6e48e6283a 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
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3957/132723 [00:00<00:03, 39563.91KB/s]
9%|8 | 11394/132723 [00:00<00:02, 60027.13KB/s]
13%|#3 | 17397/132723 [00:00<00:04, 23120.07KB/s]
19%|#8 | 24693/132723 [00:00<00:03, 33125.10KB/s]
24%|##4 | 32474/132723 [00:00<00:02, 43081.22KB/s]
29%|##9 | 38619/132723 [00:00<00:02, 46530.91KB/s]
34%|###4 | 45342/132723 [00:01<00:01, 51756.27KB/s]
39%|###8 | 51562/132723 [00:01<00:01, 50128.93KB/s]
43%|####3 | 57290/132723 [00:01<00:01, 41833.95KB/s]
49%|####9 | 65345/132723 [00:01<00:01, 50697.51KB/s]
54%|#####3 | 71192/132723 [00:01<00:01, 52193.65KB/s]
60%|#####9 | 79119/132723 [00:01<00:00, 59201.83KB/s]
66%|######5 | 87005/132723 [00:01<00:00, 64507.84KB/s]
71%|#######1 | 94894/132723 [00:01<00:00, 68508.63KB/s]
78%|#######7 | 102863/132723 [00:01<00:00, 71680.20KB/s]
83%|########3
| 110774/132723 [00:02<00:00, 73824.55KB/s]
89%|########9 | 118749/132723 [00:02<00:00, 75553.05KB/s]
95%|#########5| 126713/132723 [00:02<00:00, 76753.41KB/s]
100%|##########| 132723/132723 [00:02<00:00, 56152.71KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3729/132723 [00:00<00:03, 37047.75KB/s]
8%|8 | 10867/132723 [00:00<00:02, 57185.15KB/s]
15%|#4 | 19669/132723 [00:00<00:01, 71242.63KB/s]
21%|##1 | 28489/132723 [00:00<00:01, 77928.97KB/s]
28%|##8 | 37290/132723 [00:00<00:01, 81558.59KB/s]
35%|###4 | 46011/132723 [00:00<00:01, 83477.59KB/s]
41%|####1 | 54836/132723 [00:00<00:00, 85035.97KB/s]
48%|####8 | 63713/132723 [00:00<00:00, 86212.24KB/s]
55%|#####4 | 72524/132723 [00:00<00:00, 86802.74KB/s]
61%|######1 | 81313/132723 [00:01<00:00, 87134.58KB/s]
68%|######7 | 90118/132723 [00:01<00:00, 87410.45KB/s]
75%|#######4 | 98918/132723 [00:01<00:00, 87587.89KB/s]
81%|########1 | 107737/132723 [00:01<00:00, 87766.49KB/s]
88%|########7 | 116544/132723 [00:01<00:00, 87856.22KB/s]
94%|#########4| 125330/132723 [00:01<00:00, 87659.40KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83609.22KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 7.561 seconds)
+ **Total running time of the script:** ( 3 minutes 3.922 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 845cf75a93..e1cae3bb2a 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
@@ -5,26 +5,26 @@
Computation times
=================
-**13:53.329** total execution time for **how_to_deploy_models** files:
+**13:31.995** 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``) | 03:12.882 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:11.144 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:07.561 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:03.922 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.667 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.138 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:37.991 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.101 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.174 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:51.256 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.813 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.091 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:35.327 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.585 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.391 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:25.282 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.980 | 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 86a4252f57..61d1fe4627 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.zip22ca0192-9653-421e-83ef-25fa12f6fcbd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipe1634964-83b0-4fbc-acd1-a34b56eb4df6 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 621151cb60..b384d8bce7 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
=================
-**00:47.110** total execution time for **how_to_extend_tvm** files:
+**00:46.745** 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``) | 00:43.678 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.370 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.392 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.359 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.009 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 18cf82597f..7eb6a3db99 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: 7127us [7127us] (46.33%; 46.33%)
- FoldScaleAxis: 8256us [6us] (53.67%; 53.67%)
- FoldConstant: 8249us [1714us] (53.63%; 99.92%)
- InferType: 6535us [6535us] (42.49%; 79.22%)
+ InferType: 7046us [7046us] (46.17%; 46.17%)
+ FoldScaleAxis: 8216us [6us] (53.83%; 53.83%)
+ FoldConstant: 8210us [1682us] (53.79%; 99.92%)
+ InferType: 6528us [6528us] (42.77%; 79.51%)
@@ -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: 6581us [6581us] (45.03%; 45.03%)
- FoldScaleAxis: 8034us [5us] (54.97%; 54.97%)
- FoldConstant: 8030us [1682us] (54.94%; 99.94%)
- InferType: 6348us [6348us] (43.43%; 79.05%)
+ InferType: 6588us [6588us] (45.25%; 45.25%)
+ FoldScaleAxis: 7970us [5us] (54.75%; 54.75%)
+ FoldConstant: 7965us [1671us] (54.72%; 99.94%)
+ InferType: 6295us [6295us] (43.24%; 79.02%)
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 ea561c434c..a7bf7e9fac 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: 38.307327 ms
+ Convolution: 54.216766 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 f10e09b02c..ac3d43b1f7 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
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.366374 ms
+ conv2d with tensor core: 12.589751 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 b221074bf2..502647c3f0 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: 0.019067
- Baseline: 3.239156
+ Numpy running time: 0.018491
+ Baseline: 3.344994
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.306602
+ Opt1: 0.293475
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.334659
+ Opt2: 0.337800
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116172
+ Opt3: 0.115333
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109575
+ Opt4: 0.109859
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110681
+ Opt5: 0.110724
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147055
+ Opt6: 0.146467
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 9360f7311d..b185c4ab43 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
=================
-**00:34.693** total execution time for **how_to_optimize_operators** files:
+**00:34.562** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.897 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.977 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.621 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.510 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.175 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.075 | 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 64bb50e746..37ab445226 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
=================
-**09:11.195** total execution time for **how_to_tune_with_autoscheduler** files:
+**08:56.971** 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``) | 05:34.925 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:33.672 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:32.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:30.835 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.237 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.298 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:38.860 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:28.118 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.034 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.991 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.128 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.056 | 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 b141cb6816..e00345b689 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
@@ -239,1346 +239,482 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), 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" = 32 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(bl [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 5), 27)) && (floormod((threadIdx.x_1 + 5), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)] [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 10), 27)) && (floormod((threadIdx.x_1 + 10), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 5), 9)) && (floormod((threadIdx.x_1 + 15), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32 [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 20), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 25), 27)) && (floormod((threadIdx.x_1 + 25), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + ((floordiv(threadIdx.x_1, 3) + 1)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + (floordiv((threadIdx.x_2 + 32), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 64), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 96), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 160), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 192), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 18432)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 320), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 384), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 416), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 480), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 512), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 544)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 544), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 608)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 608), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 640), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 704), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 736)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 736), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 768), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 800)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 800), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 832), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 864)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 55296)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 928)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 928), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 960), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 992)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 992), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1024), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1056), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1088), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1184), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1216), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1248), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1312), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1376), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1408), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 92160)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1472), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1504), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1536), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1600), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1632), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1664), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1696), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1760), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1824), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1856), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1888), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1920), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1984), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2048), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2080), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2112), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2144), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2176), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2208), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2272), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2336), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2368), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2400), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2432), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2496), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2528), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 165888)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2624), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2656), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2720), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2752), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2784), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2816), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2848), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2912), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2944), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2976), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3008), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3040), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3072), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3104), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 202752)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3200), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3264), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3296), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3328), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3360), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3424), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3488), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3520), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3552), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3648), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3680), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3712), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 239616)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3776), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3840), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3872), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3936), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3968), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4000), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4096), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4128), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4160), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4192), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4224), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4288), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 276480)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4384), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4416), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4512), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4544), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4576), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 143)]))
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1634,7 +770,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.290 ms
+ Execution time of this operator: 0.361 ms
@@ -1682,35 +818,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- 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=32)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_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=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_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_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_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=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_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=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_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)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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=7)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
@@ -1731,14 +867,14 @@ 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=32)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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=4)
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=32)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1756,1192 +892,429 @@ 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__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((3 <= ((((int)threadIdx.x) + 5) % 27)) && (((((int)threadIdx.x) + 5) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((3 <= ((((int)threadIdx.x) + 10) % 27)) && (((((int)threadIdx.x) + 10) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (((((int)threadIdx.x) / 3) + 5) % 9)) && (((((int)threadIdx.x) + 15) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 5) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((3 <= ((((int)threadIdx.x) + 25) % 27)) && (((((int)threadIdx.x) + 25) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 24) {
- pad_temp_shared[(((int)threadIdx.x) + 192)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 1)] : 0.000000e+00f);
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 96) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 160) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 18432)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 608) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 800) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 55296)];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1056) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1184) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1312) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1376) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 92160)];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1760) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1824) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1888) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2336) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2528) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 165888)];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2720) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2976) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3040) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3104) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 202752)];
- kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3488) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3552) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3616) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3680) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 239616)];
- kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3872) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4064) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 276480)];
- kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4576) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -3004,7 +1377,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 34.925 seconds)
+ **Total running time of the script:** ( 5 minutes 33.672 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 8f5329f2ee..5f429bdebd 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)
- 7.8180 7.8184 7.8226 7.8130 0.0039
+ 7.8636 7.8653 7.8763 7.8493 0.0111
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.237 seconds)
+ **Total running time of the script:** ( 1 minutes 1.298 seconds)
.. _sphx_glr_download_how_to_tune_with_autoscheduler_tune_network_cuda.py:
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 91f803df36..53718ad2b2 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)
- 751.4137 751.6945 751.9176 750.6291 0.5623
+ 752.8061 751.9334 756.0780 750.4068 2.3961
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.010 seconds)
+ **Total running time of the script:** ( 1 minutes 30.835 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 dd1204f701..e34e39ff1b 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
@@ -386,13 +386,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 16) {
let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
{
- compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
+ compute_4: Buffer(compute_3, float32, [512], [])[cse_var_1] = 0f32
compute_4[(cse_var_1 + 1)] = 0f32
compute_4[(cse_var_1 + 2)] = 0f32
compute_4[(cse_var_1 + 3)] = 0f32
@@ -411,11 +411,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
+ for (i.inner: int32, 0, 16) {
let cse_var_21: int32 = (elem_idx*16)
let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256))
+ let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256))
let cse_var_17: int32 = (cse_var_20 + 9)
let cse_var_16: int32 = (cse_var_20 + 8)
let cse_var_15: int32 = (cse_var_20 + 7)
@@ -452,9 +452,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 16) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_22]), 0f32)
+ }
}
}
}
@@ -510,7 +512,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.916 ms
+ Execution time of this operator: 1.671 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 7195d0cc86..2d747776e8 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
=================
-**00:39.510** total execution time for **how_to_tune_with_autotvm** files:
+**00:35.760** 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``) | 00:39.474 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:35.724 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 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 4284926dad..5e35c353ba 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
@@ -387,7 +387,7 @@ 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 875, 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, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('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', 1500), ('unroll_explicit', 1)],None,9318192
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10294038
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -510,9 +510,8 @@ 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 875, 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, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6075339
- No: 3 GFLOPS: 12.79/12.79 result: MeasureResult(costs=(0.018096767333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.163468360900879, timestamp=1672857890.0474489) [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4276734
- No: 4 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('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', 1)],None,6597564
+ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -634,8 +633,8 @@ 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 875, 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, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8177375
- No: 5 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2828762
+ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -757,8 +756,8 @@ 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 875, 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, 8, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2444953
- No: 6 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9193683
+ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -880,8 +879,8 @@ 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 875, 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, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8284660
- No: 7 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4761515
+ No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1003,8 +1002,9 @@ 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 875, 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, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5279969
- No: 8 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,447532
+ No: 7 GFLOPS: 4.62/4.62 result: MeasureResult(costs=(0.05015347275,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3778202533721924, timestamp=1672867686.8191133) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8793151
+ No: 8 GFLOPS: 0.00/4.62 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1126,8 +1126,9 @@ 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 875, 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, 8, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3082068
- No: 9 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8894711
+ No: 9 GFLOPS: 243.48/243.48 result: MeasureResult(costs=(0.0009508150357142856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.233347177505493, timestamp=1672867689.2612226) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8951167
+ No: 10 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1249,8 +1250,8 @@ 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 875, 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, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5223800
- No: 10 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8801019
+ No: 11 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1372,8 +1373,8 @@ 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 875, 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, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2604950
- No: 11 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6708952
+ No: 12 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1495,8 +1496,8 @@ 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 875, 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, 4, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7712315
- No: 12 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 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', 1500), ('unroll_explicit', 1)],None,9512371
+ No: 13 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1618,8 +1619,8 @@ 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 875, 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, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8869352
- No: 13 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7605574
+ No: 14 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
@@ -1707,7 +1708,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fde69211fa2
+ 12: 0x00007faa46b6cfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -1771,8 +1772,8 @@ for this template
22: _PyEval_EvalFrameDefault
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1758206
- No: 14 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ 19: _PyFunction_FastCall [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7817447
+ No: 15 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1894,8 +1895,8 @@ 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 875, 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, 8, 1, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8259883
- No: 15 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5638952
+ No: 16 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2017,8 +2018,8 @@ 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 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8939503
- No: 16 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5836988
+ No: 17 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2140,8 +2141,8 @@ 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 875, 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, 8, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5116019
- No: 17 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7174666
+ No: 18 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2263,8 +2264,8 @@ 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 875, 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, 1, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9198632
- No: 18 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2162207
+ No: 19 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2386,8 +2387,8 @@ 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 875, 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, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4997768
- No: 19 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1017815
+ No: 20 GFLOPS: 0.00/243.48 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2509,130 +2510,7 @@ 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 875, 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, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9158009
- No: 20 GFLOPS: 0.00/12.79 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 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:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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:1730
- 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:1670
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1630
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1630
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1645
- 13: operator()
- at ../src/driver/driver_api.cc:388
- 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:374
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:269
- 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:1749
- 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:1693
- 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:1617
- 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 875, 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, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10217037
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8509888
@@ -2687,9 +2565,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 8, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4276734
+ [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8951167
Finish loading 20 records
- Time cost of this operator: 0.017025
+ Time cost of this operator: 0.001195
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 fced6b1319..d5c7ed2f2e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.7 98.734 (1, 2, 10, 10, 3) 2 1 [311.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.019 0.956 (1, 6, 10, 10) 1 1 [3.019]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.978 0.31 (1, 1, 10, 10, 3) 1 1 [0.978]
- Total_time - 315.696 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.9 98.705 (1, 2, 10, 10, 3) 2 1 [308.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.085 0.986 (1, 6, 10, 10) 1 1 [3.085]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.309 (1, 1, 10, 10, 3) 1 1 [0.968]
+ Total_time - 312.953 - - - - -
@@ -397,10 +397,10 @@ 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 102.7 97.501 (1, 6, 10, 10, 1) 2 1 [102.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.694 (1, 6, 10, 10) 1 1 [1.784]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.848 0.805 (1, 3, 10, 10, 1) 1 1 [0.848]
- Total_time - 105.333 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 136.1 98.107 (1, 6, 10, 10, 1) 2 1 [136.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.785 1.287 (1, 6, 10, 10) 1 1 [1.785]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.607 (1, 3, 10, 10, 1) 1 1 [0.842]
+ Total_time - 138.727 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index ef8ed0b9ad..64d73fb037 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 97.1MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 18.3MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 28.4MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.063 seconds)
+ **Total running time of the script:** ( 1 minutes 2.491 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
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 5a2bea0bfd..49747e66d4 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/tmp4atuu1gr/images/random'
+ '/tmp/tmpxqjrpdqc/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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
: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/tmp4atuu1gr/images/target contains 8144 images
- /tmp/tmp4atuu1gr/images/random contains 5000 images
+ /tmp/tmpxqjrpdqc/images/target contains 8144 images
+ /tmp/tmpxqjrpdqc/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: 0.2023 - accuracy: 0.9280 - val_loss: 0.1379 - val_accuracy: 0.9543 - 46s/epoch - 142ms/step
+ 328/328 - 47s - loss: 0.2257 - accuracy: 0.9268 - val_loss: 0.1347 - val_accuracy: 0.9551 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.0913 - accuracy: 0.9661 - val_loss: 0.1187 - val_accuracy: 0.9607 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.1085 - accuracy: 0.9606 - val_loss: 0.1642 - val_accuracy: 0.9445 - 43s/epoch - 132ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0630 - accuracy: 0.9764 - val_loss: 0.1226 - val_accuracy: 0.9592 - 43s/epoch - 131ms/step
+ 328/328 - 43s - loss: 0.0632 - accuracy: 0.9757 - val_loss: 0.1388 - val_accuracy: 0.9592 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7fd7c444aa10>
+ <keras.callbacks.History object at 0x7f295ddc7e90>
@@ -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 38.156 seconds)
+ **Total running time of the script:** ( 4 minutes 21.802 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 9b5c07448b..ab7daf23b2 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
@@ -5,18 +5,18 @@
Computation times
=================
-**06:44.140** total execution time for **how_to_work_with_microtvm** files:
+**06:27.432** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:38.156 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:21.802 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:03.063 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:02.491 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.346 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:51.411 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.720 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.875 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.853 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.851 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 4b998c3aef..6005129497 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
=================
-**00:40.625** total execution time for **how_to_work_with_relay** files:
+**00:44.552** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.694 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.280 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:06.267 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.651 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.656 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.614 | 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 8cbd17dd21..43429b04ca 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 0x7fd7d00be0e0>
+ <function my_cuda_math_rule at 0x7f29b97934d0>
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 34b1dcff85..7714613a91 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.962** total execution time for **how_to_work_with_schedules** files:
+**00:07.955** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.467 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.381 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.100 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.225 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.600 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.577 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.580 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.556 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.114 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 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 2d30035ccb..b8f3e4e185 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp_cbbrr6o/input0.cc'\nsource_filename = \"/tmp/tmp_cbbrr6o/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/tmphb5nw7a9/input0.cc'\nsource_filename = \"/tmp/tmphb5nw7a9/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 aa9da7ccce..d068a0b0d3 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
=================
-**00:26.308** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.739** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:26.302 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.733 | 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 b4d15029a1..7858526269 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 29.00s!
+ resnet18_v1 inference graph built in 28.31s!
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 6d04420280..5653fca22c 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 19.59s!
+ yolov3-tiny inference graph built in 19.26s!
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 9d467e2ded..ad630b145d 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
=================
-**01:39.900** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.270** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.930 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.079 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.970 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:48.192 | 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 3632c3cf10..50a947bc66 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
=================
-**00:03.271** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.203** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.784 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.750 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.487 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.453 | 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 9418bfb47f..4d183fc36a 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
=================
-**00:00.873** total execution time for **topic_vta_tutorials** files:
+**00:00.805** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.470 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.430 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.403 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.375 | 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 33e0cedb5d..0d14d455f4 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -325,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.415 ms
+ Execution time of this operator: 96.509 ms
@@ -443,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.004 seconds)
+ **Total running time of the script:** ( 1 minutes 13.029 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 1db7c45ef0..04033628e6 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.22/9.22 result: MeasureResult(costs=(0.0291168478,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7684669494628906, timestamp=1672856472.871911) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 2 GFLOPS: 0.50/9.22 result: MeasureResult(costs=(0.53191402,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.765598773956299, timestamp=1672856482.3809218) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
- No: 3 GFLOPS: 12.49/12.49 result: MeasureResult(costs=(0.0214993426,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5986123085021973, timestamp=1672856482.9817994) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
- No: 4 GFLOPS: 1.22/12.49 result: MeasureResult(costs=(0.220132445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.744208574295044, timestamp=1672856487.4999487) [('tile_y', [-1, 1]), ('tile_x', [-1, 2])],None,10
- No: 5 GFLOPS: 13.45/13.45 result: MeasureResult(costs=(0.019961010999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5953924655914307, timestamp=1672856488.2134664) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
- No: 6 GFLOPS: 13.69/13.69 result: MeasureResult(costs=(0.0196026126,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5764131546020508, timestamp=1672856488.773024) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
- No: 7 GFLOPS: 8.10/13.69 result: MeasureResult(costs=(0.033140545400000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7528140544891357, timestamp=1672856490.3061776) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
- No: 8 GFLOPS: 12.65/13.69 result: MeasureResult(costs=(0.021223892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.588057279586792, timestamp=1672856490.9021792) [('tile_y', [-1, 128]), ('tile_x', [-1, 256])],None,87
- No: 9 GFLOPS: 1.55/13.69 result: MeasureResult(costs=(0.1737062358,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.981074810028076, timestamp=1672856494.0003934) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
- No: 10 GFLOPS: 13.54/13.69 result: MeasureResult(costs=(0.019830590000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5250179767608643, timestamp=1672856494.5690324) [('tile_y', [-1, 256]), ('tile_x', [-1, 64])],None,68
+ No: 1 GFLOPS: 12.70/12.70 result: MeasureResult(costs=(0.0211305812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5974962711334229, timestamp=1672866294.7512436) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+ No: 2 GFLOPS: 3.70/12.70 result: MeasureResult(costs=(0.07245523779999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.411741018295288, timestamp=1672866296.1615012) [('tile_y', [-1, 128]), ('tile_x', [-1, 16])],None,47
+ No: 3 GFLOPS: 10.48/12.70 result: MeasureResult(costs=(0.025617061400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7353250980377197, timestamp=1672866297.5811481) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
+ No: 4 GFLOPS: 9.80/12.70 result: MeasureResult(costs=(0.0273793532,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6683676242828369, timestamp=1672866299.0269263) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 5 GFLOPS: 14.74/14.74 result: MeasureResult(costs=(0.018209714199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8473269939422607, timestamp=1672866299.9880056) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
+ No: 6 GFLOPS: 12.60/14.74 result: MeasureResult(costs=(0.021305468200000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5954391956329346, timestamp=1672866300.5832536) [('tile_y', [-1, 64]), ('tile_x', [-1, 256])],None,86
+ No: 7 GFLOPS: 13.86/14.74 result: MeasureResult(costs=(0.0193675232,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5824456214904785, timestamp=1672866301.8951266) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 8 GFLOPS: 12.35/14.74 result: MeasureResult(costs=(0.021734008800000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6016209125518799, timestamp=1672866302.495635) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+ No: 9 GFLOPS: 2.27/14.74 result: MeasureResult(costs=(0.1182720832,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.098576784133911, timestamp=1672866304.7117898) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
+ No: 10 GFLOPS: 1.54/14.74 result: MeasureResult(costs=(0.1739183466,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.996886730194092, timestamp=1672866307.7529945) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 9724fb44a7..1a24f85ef8 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': 509.3304875500053, 'median': 509.9731662500062, 'std': 1.9299450893361774}
+ {'mean': 512.2844568400012, 'median': 512.1762151999974, 'std': 1.484752293193894}
@@ -554,31 +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: 4.27/ 11.07 GFLOPS | Progress: (4/20) | 9.80 s
[Task 1/25] Current/Best: 8.63/ 22.85 GFLOPS | Progress: (8/20) | 13.74 s
[Task 1/25] Current/Best: 5.77/ 22.85 GFLOPS | Progress: (12/20) | 18.76 s
[Task 1/25] Current/Best: 8.50/ 22.85 GFLOPS | Progress: (16/20) | 22.93 s
[Task 1/25] Current/Best: 9.55/ 22.85 GFLOPS | Progress: (20/20) | 25.12 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 4.65/ 16.94 GFLOPS | Progress: (4/20) | 3.73 s
[Task 2/25] Current/Best: 13.47/ 16.94 GFLOPS | Progress: (8/20) | 6.00 s
[Task 2/25] Current/Best: 13.60/ 16.94 GFLOPS | Progress: (12/20) | 7.80 s
[Task 2/25] Current/Best: 16.33/ 16.94 GFLOPS | Progress: (16/20) | 10.16 s
[Task 2/25] Current/Best: 9.99/ 20.55 GFLOPS | Progress: (20/20) | 11.89 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 3.14/ 9.95 GFLOPS | Progress: (4/20) | 5.61 s
[Task 3/25] Current/Best: 10.35/ 23.96 GFLOPS | Progress: (8/20) | 7.65 s
[Task 3/25] Current/Best: 15.87/ 23.96 GFLOPS | Progress: (12/20) | 10.33 s
[Task 3/25] Current/Best: 16.51/ 23.96 GFLOPS | Progress: (16/20) | 13.26 s
[Task 3/25] Current/Best: 8.26/ 23.96 GFLOPS | Progress: (20/20) | 15.76 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 2.37/ 17.43 GFLOPS | Progress: (4/20) | 4.19 s
[Task 4/25] Current/Best: 15.75/ 17.44 GFLOPS | Progress: (8/20) | 9.10 s
[Task 4/25] Current/Best: 13.30/ 21.22 GFLOPS | Progress: (12/20) | 12.22 s
[Task 4/25] Current/Best: 3.81/ 21.22 GFLOPS | Progress: (16/20) | 14.72 s
[Task 4/25] Current/Best: 8.27/ 21.22 GFLOPS | Progress: (20/20) | 16.99 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.35/ 17.62 GFLOPS | Progress: (4/20) | 3.60 s
[Task 5/25] Current/Best: 4.56/ 17.62 GFLOPS | Progress: (8/20) | 5.84 s
[Task 5/25] Current/Best: 18.07/ 18.07 GFLOPS | Progress: (12/20) | 7.65 s
[Task 5/25] Current/Best: 6.02/ 22.15 GFLOPS | Progress: (16/20) | 10.27 s
[Task 5/25] Current/Best: 15.52/ 22.15 GFLOPS | Progress: (20/20) | 12.28 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.38/ 18.12 GFLOPS | Progress: (4/20) | 6.86 s
[Task 6/25] Current/Best: 4.38/ 19.97 GFLOPS | Progress: (8/20) | 9.41 s
[Task 6/25] Current/Best: 16.21/ 19.97 GFLOPS | Progress: (12/20) | 13.55 s
[Task 6/25] Current/Best: 5.80/ 19.97 GFLOPS | Progress: (16/20) | 21.57 s
[Task 6/25] Current/Best: 10.73/ 19.97 GFLOPS | Progress: (20/20) | 25.35 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.14/ 12.72 GFLOPS | Progress: (4/20) | 4.92 s
[Task 7/25] Current/Best: 19.05/ 20.06 GFLOPS | Progress: (8/20) | 6.89 s
[Task 7/25] Current/Best: 11.71/ 20.06 GFLOPS | Progress: (12/20) | 10.07 s
[Task 7/25] Current/Best: 11.69/ 20.06 GFLOPS | Progress: (16/20) | 13.40 s
[Task 7/25] Current/Best: 11.40/ 20.06 GFLOPS | Progress: (20/20) | 15.99 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.69/ 20.84 GFLOPS | Progress: (4/20) | 4.02 s
[Task 8/25] Current/Best: 12.88/ 20.84 GFLOPS | Progress: (8/20) | 8.75 s
[Task 8/25] Current/Best: 16.00/ 20.84 GFLOPS | Progress: (12/20) | 20.26 s
[Task 8/25] Current/Best: 12.17/ 20.84 GFLOPS | Progress: (16/20) | 25.78 s
[Task 8/25] Current/Best: 10.05/ 20.84 GFLOPS | Progress: (20/20) | 33.25 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.86/ 16.94 GFLOPS | Progress: (4/20) | 12.87 s
[Task 9/25] Current/Best: 8.15/ 16.94 GFLOPS | Progress: (8/20) | 20.32 s
[Task 9/25] Current/Best: 14.28/ 16.94 GFLOPS | Progress: (12/20) | 22.57 s
[Task 9/25] Current/Best: 3.20/ 16.94 GFLOPS | Progress: (16/20) | 33.97 s
[Task 9/25] Current/Best: 16.50/ 20.42 GFLOPS | Progress: (20/
20) | 36.23 s
[Task 10/25] 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: 11.29/ 23.73 GFLOPS | Progress: (4/20) | 9.59 s
[Task 1/25] Current/Best: 15.33/ 23.73 GFLOPS | Progress: (8/20) | 13.41 s
[Task 1/25] Current/Best: 17.59/ 23.73 GFLOPS | Progress: (12/20) | 16.76 s
[Task 1/25] Current/Best: 8.41/ 23.73 GFLOPS | Progress: (16/20) | 20.21 s
[Task 1/25] Current/Best: 10.97/ 23.73 GFLOPS | Progress: (20/20) | 26.46 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 6.60/ 16.77 GFLOPS | Progress: (4/20) | 3.36 s
[Task 2/25] Current/Best: 13.87/ 16.77 GFLOPS | Progress: (8/20) | 5.59 s
[Task 2/25] Current/Best: 6.28/ 22.70 GFLOPS | Progress: (12/20) | 7.09 s
[Task 2/25] Current/Best: 18.54/ 22.70 GFLOPS | Progress: (16/20) | 8.99 s
[Task 2/25] Current/Best: 17.32/ 22.70 GFLOPS | Progress: (20/20) | 11.86 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.77/ 15.97 GFLOPS | Progress: (4/20) | 3.95 s
[Task 3/25] Current/Best: 12.94/ 17.64 GFLOPS | Progress: (8/20) | 6.35 s
[Task 3/25] Current/Best: 14.76/ 19.29 GFLOPS | Progress: (12/20) | 8.32 s
[Task 3/25] Current/Best: 12.46/ 19.29 GFLOPS | Progress: (16/20) | 10.49 s
[Task 3/25] Current/Best: 15.56/ 20.04 GFLOPS | Progress: (20/20) | 12.42 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.75/ 12.75 GFLOPS | Progress: (4/20) | 3.93 s
[Task 4/25] Current/Best: 8.36/ 14.80 GFLOPS | Progress: (8/20) | 9.52 s
[Task 4/25] Current/Best: 11.17/ 14.80 GFLOPS | Progress: (12/20) | 16.72 s
[Task 4/25] Current/Best: 12.30/ 18.72 GFLOPS | Progress: (16/20) | 18.94 s
[Task 4/25] Current/Best: 13.88/ 18.72 GFLOPS | Progress: (20/20) | 20.75 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 4.58/ 10.55 GFLOPS | Progress: (4/20) | 3.96 s
[Task 5/25] Current/Best: 5.75/ 18.45 GFLOPS | Progress: (8/20) | 5.68 s
[Task 5/25] Current/Best: 15.12/ 18.45 GFLOPS | Progress: (12/20) | 7.46 s
[Task 5/25] Current/Best: 23.10/ 23.10 GFLOPS | Progress: (16/20) | 9.47 s
[Task 5/25] Current/Best: 16.60/ 23.10 GFLOPS | Progress: (20/20) | 11.73 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 15.38/ 17.28 GFLOPS | Progress: (4/20) | 5.50 s
[Task 6/25] Current/Best: 5.11/ 17.69 GFLOPS | Progress: (8/20) | 8.51 s
[Task 6/25] Current/Best: 8.66/ 17.69 GFLOPS | Progress: (12/20) | 11.83 s
[Task 6/25] Current/Best: 8.51/ 17.69 GFLOPS | Progress: (16/20) | 14.31 s
[Task 6/25] Current/Best: 8.52/ 17.69 GFLOPS | Progress: (20/20) | 16.78 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.06/ 14.07 GFLOPS | Progress: (4/20) | 4.12 s
[Task 7/25] Current/Best: 7.21/ 16.81 GFLOPS | Progress: (8/20) | 7.82 s
[Task 7/25] Current/Best: 20.02/ 20.02 GFLOPS | Progress: (12/20) | 10.21 s
[Task 7/25] Current/Best: 12.30/ 20.02 GFLOPS | Progress: (16/20) | 13.09 s
[Task 7/25] Current/Best: 6.31/ 20.02 GFLOPS | Progress: (20/20) | 15.68 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.71/ 18.68 GFLOPS | Progress: (4/20) | 5.99 s
[Task 8/25] Current/Best: 14.35/ 18.68 GFLOPS | Progress: (8/20) | 11.98 s
[Task 8/25] Current/Best: 14.43/ 18.68 GFLOPS | Progress: (12/20) | 14.45 s
[Task 8/25] Current/Best: 9.98/ 18.68 GFLOPS | Progress: (16/20) | 21.61 s
[Task 8/25] Current/Best: 11.22/ 18.68 GFLOPS | Progress: (20/20) | 26.83 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 19.39/ 19.39 GFLOPS | Progress: (4/20) | 3.72 s
[Task 9/25] Current/Best: 11.11/ 19.39 GFLOPS | Progress: (8/20) | 5.86 s
[Task 9/25] Current/Best: 7.37/ 19.39 GFLOPS | Progress: (12/20) | 7.77 s
[Task 9/25] Current/Best: 16.55/ 19.39 GFLOPS | Progress: (16/20) | 9.54 s
[Task 9/25] Current/Best: 11.33/ 19.39 GFLOPS | Progress: (20/20) | 20.65 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (4/20) | 4.25 s
[Task 10/25] Current/Best: 10.25/ 20.12 GFLOPS | Progress: (8/20) | 6.12 s
[Task 10/25] Current/Best: 15.11/ 20.12 GFLOPS | Progress: (12/20) | 8.05 s
[Task 10/25] Current/Best: 13.34/ 20.12 GFLOPS | Progress: (16/20) | 9.84 s
[Task 10/25] Current/Best: 16.63/ 20.12 GFLOPS | Progress: (20/20) |
12.22 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 24.22/ 24.22 GFLOPS | Progress: (4/20) | 5.18 s
[Task 11/25] Current/Best: 11.88/ 24.22 GFLOPS | Progress: (8/20) | 7.68 s
[Task 11/25] Current/Best: 12.33/ 24.22 GFLOPS | Progress: (12/20) | 10.40 s
[Task 11/25] Current/Best: 7.63/ 24.22 GFLOPS | Progress: (16/20) | 12.86 s
[Task 11/25] Current/Best: 9.81/ 24.22 GFLOPS | Progress: (20/20) | 15.31 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.06/ 15.78 GFLOPS | Progress: (4/20) | 4.30 s
[Task 12/25] Current/Best: 11.39/ 15.78 GFLOPS | Progress: (8/20) | 6.85 s
[Task 12/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (12/20) | 10.49 s
[Task 12/25] Current/Best: 13.43/ 16.19 GFLOPS | Progress: (16/20) | 13.17 s
[Task 12/25] Current/Best: 14.72/ 16.19 GFLOPS | Progress: (20/20) | 15.81 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 3.07/ 19.98 GFLOPS | Progress: (4/20) | 5.87 s
[Task 13/25] Current/Best: 10.00/ 19.98 GFLOPS | Progress: (8/20) | 9.09 s
[Task 13/25] Current/Best: 17.54/ 19.98 GFLOPS | Progress: (12/20) | 11.90 s
[Task 13/25] Current/Best: 10.78/ 19.98 GFLOPS | Progress: (16/20) | 15.06 s
[Task 13/25] Current/Best: 6.53/ 20.09 GFLOPS | Progress: (20/20) | 19.31 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 10.38/ 11.11 GFLOPS | Progress: (4/20) | 5.01 s
[Task 14/25] Current/Best: 13.84/ 14.18 GFLOPS | Progress: (8/20) | 9.48 s
[Task 14/25] Current/Best: 4.17/ 19.45 GFLOPS | Progress: (12/20) | 12.06 s
[Task 14/25] Current/Best: 13.01/ 19.45 GFLOPS | Progress: (16/20) | 15.45 s
[Task 14/25] Current/Best: 13.07/ 19.45 GFLOPS | Progress: (20/20) | 18.74 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 10/25] Current/Best: 13.18/ 13.43 GFLOPS | Progress: (4/20) | 3.64 s
[Task 10/25] Current/Best: 8.73/ 15.29 GFLOPS | Progress: (8/20) | 5.47 s
[Task 10/25] Current/Best: 15.62/ 15.62 GFLOPS | Progress: (12/20) | 7.17 s
[Task 10/25] Current/Best: 5.72/ 15.62 GFLOPS | Progress: (16/20) | 11.00 s
[Task 10/25] Current/Best: 13.47/ 15.62 GFLOPS | Progress: (20/20) | 13.39 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.95/ 12.97 GFLOPS | Progress: (4/20) | 4.37 s
[Task 11/25] Current/Best: 3.14/ 18.43 GFLOPS | Progress: (8/20) | 7.05 s
[Task 11/25] Current/Best: 19.84/ 19.84 GFLOPS | Progress: (12/20) | 9.45 s
[Task 11/25] Current/Best: 12.70/ 19.84 GFLOPS | Progress: (16/20) | 12.10 s
[Task 11/25] Current/Best: 15.03/ 19.84 GFLOPS | Progress: (20/20) | 14.24 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.26/ 21.82 GFLOPS | Progress: (4/20) | 4.90 s
[Task 12/25] Current/Best: 11.14/ 21.82 GFLOPS | Progress: (8/20) | 7.02 s
[Task 12/25] Current/Best: 11.04/ 21.82 GFLOPS | Progress: (12/20) | 10.04 s
[Task 12/25] Current/Best: 15.28/ 21.82 GFLOPS | Progress: (16/20) | 12.12 s
[Task 12/25] Current/Best: 15.55/ 21.82 GFLOPS | Progress: (20/20) | 14.72 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 1.57/ 20.03 GFLOPS | Progress: (4/20) | 5.84 s
[Task 13/25] Current/Best: 6.10/ 20.03 GFLOPS | Progress: (8/20) | 9.92 s
[Task 13/25] Current/Best: 18.55/ 20.03 GFLOPS | Progress: (12/20) | 13.06 s
[Task 13/25] Current/Best: 11.09/ 20.03 GFLOPS | Progress: (16/20) | 16.87 s
[Task 13/25] Current/Best: 15.78/ 20.03 GFLOPS | Progress: (20/20) | 19.66 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 8.10/ 13.82 GFLOPS | Progress: (4/20) | 4.30 s
[Task 14/25] Current/Best: 9.52/ 16.13 GFLOPS | Progress: (8/20) | 8.22 s
[Task 14/25] Current/Best: 9.38/ 16.13 GFLOPS | Progress: (12/20) | 15.02 s
[Task 14/25] Current/Best: 18.62/ 18.62 GFLOPS | Progress: (16/20) | 17.61 s
[Task 14/25] Current/Best: 12.57/ 18.62 GFLOPS | Progress: (20/20) | 20.03 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 17.59/ 18.44 GFLOPS | Progress: (4/20) | 4.05 s
[Task 15/25] Current/Best: 15.11/ 18.44 GFLOPS | Progress: (8/20) | 5.51 s
[Task 15/25] Current/Best: 10.12/ 18.46 GFLOPS | Progress: (12/20) | 7.81 s
[Task 15/25] Current/Best: 2.99/ 18.46 GFLOPS | Progress: (16/20) | 9.81 s Done.
-
[Task 15/25] Current/Best: 11.45/ 18.46 GFLOPS | Progress: (20/20) | 12.07 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 11.89/ 17.08 GFLOPS | Progress: (4/20) | 4.80 s
[Task 16/25] Current/Best: 14.53/ 19.52 GFLOPS | Progress: (8/20) | 6.56 s
[Task 16/25] Current/Best: 7.58/ 19.52 GFLOPS | Progress: (12/20) | 10.08 s
[Task 16/25] Current/Best: 15.76/ 19.52 GFLOPS | Progress: (16/20) | 13.20 s
[Task 16/25] Current/Best: 15.58/ 19.52 GFLOPS | Progress: (20/20) | 14.96 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 6.50/ 11.33 GFLOPS | Progress: (4/20) | 6.09 s
[Task 17/25] Current/Best: 16.24/ 19.63 GFLOPS | Progress: (8/20) | 8.76 s
[Task 17/25] Current/Best: 3.10/ 21.27 GFLOPS | Progress: (12/20) | 11.24 s
[Task 17/25] Current/Best: 10.25/ 21.27 GFLOPS | Progress: (16/20) | 13.41 s
[Task 17/25] Current/Best: 23.39/ 23.39 GFLOPS | Progress: (20/20) | 16.78 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.85/ 15.45 GFLOPS | Progress: (4/20) | 4.07 s
[Task 18/25] Current/Best: 8.34/ 15.45 GFLOPS | Progress: (8/20) | 8.72 s
[Task 18/25] Current/Best: 6.04/ 15.45 GFLOPS | Progress: (12/20) | 15.07 s
[Task 18/25] Current/Best: 6.00/ 16.37 GFLOPS | Progress: (16/20) | 18.02 s
[Task 18/25] Current/Best: 5.64/ 21.62 GFLOPS | Progress: (20/20) | 22.59 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 19.33/ 19.33 GFLOPS | Progress: (4/20) | 5.20 s
[Task 19/25] Current/Best: 11.47/ 19.33 GFLOPS | Progress: (8/20) | 8.48 s
[Task 19/25] Current/Best: 10.57/ 19.33 GFLOPS | Progress: (12/20) | 11.90 s
[Task 19/25] Current/Best: 9.54/ 19.33 GFLOPS | Progress: (16/20) | 15.90 s
[Task 19/25] Current/Best: 10.37/ 19.33 GFLOPS | Progress: (20/20) | 19.63 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.20/ 16.12 GFLOPS | Progress: (4/20) | 4.80 s
[Task 20/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (8/20) | 6.96 s
[Task 20/25] Current/Best: 4.41/ 18.90 GFLOPS | Progress: (12/20) | 9.21 s
[Task 20/25] Current/Best: 18.69/ 18.90 GFLOPS | Progress: (16/20) | 11.62 s
[Task 20/25] Current/Best: 2.31/ 18.90 GFLOPS | Progress: (20/20) | 14.43 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 3.77 s
[Task 21/25] Current/Best: 5.31/ 21.03 GFLOPS | Progress: (8/20) | 6.15 s
[Task 21/25] Current/Best: 7.06/ 21.03 GFLOPS | Progress: (12/20) | 10.95 s
[Task 21/25] Current/Best: 14.35/ 21.03 GFLOPS | Progress: (16/20) | 12.89 s
[Task 21/25] Current/Best: 17.76/ 21.03 GFLOPS | Progress: (20/20)
| 16.23 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 11.82/ 17.88 GFLOPS | Progress: (4/20) | 3.69 s Done.
+
[Task 15/25] Current/Best: 7.55/ 12.30 GFLOPS | Progress: (4/20) | 5.01 s
[Task 15/25] Current/Best: 9.30/ 20.42 GFLOPS | Progress: (8/20) | 11.85 s
[Task 15/25] Current/Best: 3.18/ 20.42 GFLOPS | Progress: (12/20) | 15.78 s
[Task 15/25] Current/Best: 8.94/ 20.42 GFLOPS | Progress: (16/20) | 18.01 s
[Task 15/25] Current/Best: 14.59/ 20.42 GFLOPS | Progress: (20/20) | 23.79 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.03/ 16.38 GFLOPS | Progress: (4/20) | 4.38 s
[Task 16/25] Current/Best: 15.04/ 20.33 GFLOPS | Progress: (8/20) | 6.13 s
[Task 16/25] Current/Best: 12.35/ 20.33 GFLOPS | Progress: (12/20) | 8.10 s
[Task 16/25] Current/Best: 14.40/ 20.33 GFLOPS | Progress: (16/20) | 10.35 s
[Task 16/25] Current/Best: 8.20/ 20.33 GFLOPS | Progress: (20/20) | 13.90 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 7.79/ 18.22 GFLOPS | Progress: (4/20) | 5.99 s
[Task 17/25] Current/Best: 17.15/ 18.22 GFLOPS | Progress: (8/20) | 9.32 s
[Task 17/25] Current/Best: 8.20/ 19.94 GFLOPS | Progress: (12/20) | 12.97 s
[Task 17/25] Current/Best: 3.09/ 19.94 GFLOPS | Progress: (16/20) | 16.28 s
[Task 17/25] Current/Best: 21.46/ 21.46 GFLOPS | Progress: (20/20) | 18.59 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 17.77/ 18.93 GFLOPS | Progress: (4/20) | 5.71 s
[Task 18/25] Current/Best: 15.31/ 18.93 GFLOPS | Progress: (8/20) | 7.62 s
[Task 18/25] Current/Best: 6.80/ 18.93 GFLOPS | Progress: (12/20) | 14.27 s
[Task 18/25] Current/Best: 14.76/ 20.10 GFLOPS | Progress: (16/20) | 16.68 s
[Task 18/25] Current/Best: 17.13/ 20.10 GFLOPS | Progress: (20/20) | 22.62 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.30/ 18.30 GFLOPS | Progress: (4/20) | 5.84 s
[Task 19/25] Current/Best: 11.28/ 18.96 GFLOPS | Progress: (8/20) | 8.07 s
[Task 19/25] Current/Best: 19.61/ 19.61 GFLOPS | Progress: (12/20) | 11.07 s
[Task 19/25] Current/Best: 11.87/ 20.61 GFLOPS | Progress: (16/20) | 15.16 s
[Task 19/25] Current/Best: 13.22/ 20.61 GFLOPS | Progress: (20/20) | 17.41 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 13.02/ 15.01 GFLOPS | Progress: (4/20) | 4.09 s
[Task 20/25] Current/Best: 8.14/ 15.01 GFLOPS | Progress: (8/20) | 8.04 s
[Task 20/25] Current/Best: 14.70/ 15.11 GFLOPS | Progress: (12/20) | 10.96 s
[Task 20/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (16/20) | 12.77 s
[Task 20/25] Current/Best: 11.84/ 18.94 GFLOPS | Progress: (20/20) | 16.38 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 14.45/ 15.02 GFLOPS | Progress: (4/20) | 4.33 s
[Task 21/25] Current/Best: 16.09/ 16.59 GFLOPS | Progress: (8/20) | 6.56 s
[Task 21/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (12/20) | 8.29 s Done.
Done.
-
[Task 22/25] Current/Best: 16.83/ 17.88 GFLOPS | Progress: (8/20) | 5.97 s
[Task 22/25] Current/Best: 18.01/ 18.56 GFLOPS | Progress: (12/20) | 7.53 s
[Task 22/25] Current/Best: 19.91/ 19.91 GFLOPS | Progress: (16/20) | 9.09 s
[Task 22/25] Current/Best: 13.84/ 19.91 GFLOPS | Progress: (20/20) | 11.40 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.29/ 17.29 GFLOPS | Progress: (4/20) | 4.67 s
[Task 23/25] Current/Best: 19.43/ 24.15 GFLOPS | Progress: (8/20) | 7.81 s
[Task 23/25] Current/Best: 9.67/ 24.15 GFLOPS | Progress: (12/20) | 11.21 s
[Task 23/25] Current/Best: 10.26/ 24.15 GFLOPS | Progress: (16/20) | 14.09 s
[Task 23/25] Current/Best: 9.87/ 24.15 GFLOPS | Progress: (20/20) | 18.81 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 3.02/ 3.81 GFLOPS | Progress: (8/20) | 23.72 s
[Task 24/25] Current/Best: 3.44/ 7.46 GFLOPS | Progress: (12/20) | 26.34 s
[Task 24/25] Current/Best: 5.48/ 10.56 GFLOPS | Progress: (16/20) | 28.47 s
[Task 24/25] Current/Best: 6.79/ 10.56 GFLOPS | Progress: (20/20) | 39.40 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 8.78/ 9.12 GFLOPS | Progress: (4/20) | 7.26 s
[Task 25/25] Current/Best: 3.28/ 9.12 GFLOPS | Progress: (8/20) | 12.10 s
[Task 25/25] Current/Best: 7.94/ 9.98 GFLOPS | Progress: (12/20) | 18.07 s
[Task 25/25] Current/Best: 9.98/ 9.98 GFLOPS | Progress: (16/20) | 28.98 s
[Task 25/25] Current/Best: 3.52/ 9.98 GFLOPS | Progress: (20/20) | 39.91 s
+
[Task 21/25] Current/Best: 16.40/ 21.30 GFLOPS | Progress: (16/20) | 10.84 s
[Task 21/25] Current/Best: 15.75/ 22.38 GFLOPS | Progress: (20/20) | 12.44 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 6.17/ 14.86 GFLOPS | Progress: (4/20) | 4.12 s
[Task 22/25] Current/Best: 10.07/ 23.11 GFLOPS | Progress: (8/20) | 6.64 s
[Task 22/25] Current/Best: 11.67/ 23.11 GFLOPS | Progress: (12/20) | 8.43 s
[Task 22/25] Current/Best: 10.64/ 23.11 GFLOPS | Progress: (16/20) | 10.16 s
[Task 22/25] Current/Best: 11.70/ 23.11 GFLOPS | Progress: (20/20) | 13.49 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 5.38/ 19.82 GFLOPS | Progress: (4/20) | 5.71 s
[Task 23/25] Current/Best: 8.11/ 22.06 GFLOPS | Progress: (8/20) | 8.25 s
[Task 23/25] Current/Best: 10.38/ 22.06 GFLOPS | Progress: (12/20) | 12.07 s
[Task 23/25] Current/Best: 14.28/ 22.06 GFLOPS | Progress: (16/20) | 16.21 s
[Task 23/25] Current/Best: 22.34/ 22.34 GFLOPS | Progress: (20/20) | 18.69 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.95/ 1.95 GFLOPS | Progress: (4/20) | 12.45 s
[Task 24/25] Current/Best: 1.82/ 9.19 GFLOPS | Progress: (8/20) | 23.39 s
[Task 24/25] Current/Best: 3.02/ 9.19 GFLOPS | Progress: (12/20) | 34.33 s
[Task 24/25] Current/Best: 6.76/ 9.19 GFLOPS | Progress: (16/20) | 41.31 s
[Task 24/25] Current/Best: 4.14/ 9.19 GFLOPS | Progress: (20/20) | 51.98 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 9.17/ 9.17 GFLOPS | Progress: (4/20) | 13.86 s
[Task 25/25] Current/Best: 3.52/ 9.17 GFLOPS | Progress: (8/20) | 22.35 s
[Task 25/25] Current/Best: 9.30/ 9.38 GFLOPS | Progress: (12/20) | 30.37 s
[Task 25/25] Current/Best: 8.63/ 9.38 GFLOPS | Progress: (16/20) | 41.35 s
[Task 25/25] Current/Best: 8.91/ 9.99 GFLOPS | Progress: (20/20) | 53.06 s
@@ -674,8 +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=0.356380
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -732,8 +732,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 423.3795222200115, 'median': 422.2240747500564, 'std': 2.740680352736261}
- unoptimized: {'mean': 509.3304875500053, 'median': 509.9731662500062, 'std': 1.9299450893361774}
+ optimized: {'mean': 423.6158692200024, 'median': 422.660785100004, 'std': 2.5831245688281905}
+ unoptimized: {'mean': 512.2844568400012, 'median': 512.1762151999974, 'std': 1.484752293193894}
@@ -756,7 +756,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 49.362 seconds)
+ **Total running time of the script:** ( 11 minutes 55.732 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 afbcc4c83a..9ad55dae23 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.301e-07 secs/op
+ 1.245e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 2f52177df2..dcaf133407 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xcba8ab0)), stage(b, placeholder(b, 0x97d5ed0)), 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, 0x22ca2b90)), stage(b, placeholder(b, 0xc51afd0)), 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 a770417255..74f53db556 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**15:05.670** total execution time for **tutorial** files:
+**15:02.913** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:49.362 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:55.732 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:16.004 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:13.029 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.080 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.044 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.969 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.538 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:26.637 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.118 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.832 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.460 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.608 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.818 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.169 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.163 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.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 bae3d4ad27..c702a582ae 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: 0.000009
+ Numpy running time: 0.000007
+ naive: 0.000007
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000008
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.652610001969151e-06 1.0
- naive 8.5725e-06 1.120206047060303
- parallel 8.1586e-06 1.066119924823119
- vector 2.4555600000000003e-05 3.2087875892906363
+ numpy 7.360390000030747e-06 1.0
+ naive 6.6658e-06 0.9056313592040849
+ parallel 6.9437999999999995e-06 0.9434010969488019
+ vector 2.45766e-05 3.33903502394538
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018320
+ Numpy running time: 0.018314
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.202920
+ none: 3.345508
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.299372
+ blocking: 0.306115
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.330393
+ vectorization: 0.340074
@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, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.112877
+ loop permutation: 0.111738
@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, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107930
+ array packing: 0.107207
@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, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110419
+ block caching: 0.109948
@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, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145790
+ parallelization: 0.145978
@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, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2029196510999993 1.0
- blocking 0.29937207720000003 0.09346849431492443
- vectorization 0.330393405 0.10315382244650778
- loop permutation 0.11287704369999998 0.03524192174512835
- array packing 0.1079300007 0.033697380033536874
- block caching 0.110419333 0.034474587260432205
- parallelization 0.145789979 0.045517838372851595
+ none 3.3455076655999996 1.0
+ blocking 0.30611520740000003 0.09150037542810407
+ vectorization 0.3400738466 0.10165089445072592
+ loop permutation 0.11173799100000001 0.033399412635917655
+ array packing 0.1072068998 0.03204503188031793
+ block caching 0.1099479824 0.03286436421310109
+ parallelization 0.14597778379999998 0.04363397080240126
@@ -1652,6 +1652,11 @@ 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 0.044 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 33bb246535..f45888a73e 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-52fe2685747ab17960818694b5592125a1ab608d
+116453f5cfc51e4682589b8e30bc87e738e44556
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index a1b792ea4b..fe8f0cc9a1 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ 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 9.048 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.908 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 70df51fc83..86c2ee6e4a 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ 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 930ms/step
+1/1 [==============================] - 1s 939ms/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 0a943c444d..3e7fe256d3 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ 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.zipcd5cfa5d-5860-4fdf-8e3a-c90ec05901d1 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.zip8e39e356-cb66-478a-a46c-4a137e0df0d7 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 e484e9cbca..92444a8a04 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,11 +448,12 @@ 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]
- 20%|#9 | 8.12M/41.5M [00:00<00:00, 84.6MB/s]
- 39%|###9 | 16.2M/41.5M [00:00<00:00, 71.7MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 66.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 92.8MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 85.0MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 52.8MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 52.7MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 53.6MB/s]
+ 75%|#######5 | 31.2M/41.5M [00:00<00:00, 66.0MB/s]
+ 91%|#########1| 37.8M/41.5M [00:00<00:00, 46.3MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 51.1MB/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 3d480b57ce..4defd5ca71 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,10 @@ be unstable.</p>
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]
- 22%|##2 | 9.98M/44.7M [00:00<00:00, 105MB/s]
- 52%|#####2 | 23.3M/44.7M [00:00<00:00, 125MB/s]
- 79%|#######8 | 35.2M/44.7M [00:00<00:00, 112MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 110MB/s]
+ 28%|##7 | 12.4M/44.7M [00:00<00:00, 130MB/s]
+ 56%|#####5 | 24.8M/44.7M [00:00<00:00, 111MB/s]
+ 80%|#######9 | 35.5M/44.7M [00:00<00:00, 106MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 107MB/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 aa40b4b97d..30c55089e4 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ 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 11.097 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.600 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 55d6ee8c07..dea7151cb2 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:38.551</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:40.675</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<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>01:11.097</p></td>
+<td><p>01:11.600</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>01:09.048</p></td>
+<td><p>01:08.908</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>00:45.831</p></td>
+<td><p>00:46.877</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>00:31.372</p></td>
+<td><p>00:32.324</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>00:28.454</p></td>
+<td><p>00:28.704</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>00:26.121</p></td>
+<td><p>00:25.834</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>00:25.052</p></td>
+<td><p>00:24.947</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>00:22.330</p></td>
+<td><p>00:22.201</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:16.840</p></td>
+<td><p>00:16.886</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>00:02.406</p></td>
+<td><p>00:02.395</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 17a96230be..cf918d25e5 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,7 +919,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2544.7204 2544.3257 2547.5219 2542.4330 1.6902
+ 2754.8814 2754.7721 2757.5498 2753.2221 1.3234
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 f75a42dccd..245a1c7d93 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.6435 15.6362 15.7886 15.5259 0.0888
+ 16.9005 16.8900 17.9896 15.7231 0.5978
</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 3f0bf7fe04..f476dd869f 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,23 +453,21 @@ be unstable.</p>
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]
- 5%|4 | 8.02M/170M [00:00<00:02, 84.1MB/s]
- 13%|#2 | 21.5M/170M [00:00<00:01, 118MB/s]
- 19%|#9 | 32.7M/170M [00:00<00:01, 114MB/s]
- 26%|##5 | 43.6M/170M [00:00<00:01, 113MB/s]
- 32%|###2 | 54.5M/170M [00:00<00:01, 114MB/s]
- 38%|###8 | 65.4M/170M [00:00<00:01, 108MB/s]
- 45%|####4 | 75.7M/170M [00:00<00:00, 106MB/s]
- 51%|##### | 85.8M/170M [00:00<00:00, 104MB/s]
- 56%|#####6 | 95.8M/170M [00:00<00:00, 103MB/s]
- 62%|######2 | 106M/170M [00:01<00:00, 93.8MB/s]
- 68%|######7 | 115M/170M [00:01<00:00, 93.2MB/s]
- 75%|#######5 | 128M/170M [00:01<00:00, 106MB/s]
- 81%|########1 | 138M/170M [00:01<00:00, 98.4MB/s]
- 88%|########8 | 150M/170M [00:01<00:00, 105MB/s]
- 94%|#########4| 160M/170M [00:01<00:00, 103MB/s]
-100%|#########9| 170M/170M [00:01<00:00, 102MB/s]
-100%|##########| 170M/170M [00:01<00:00, 103MB/s]
+ 8%|7 | 12.9M/170M [00:00<00:01, 135MB/s]
+ 15%|#5 | 25.8M/170M [00:00<00:01, 91.7MB/s]
+ 24%|##3 | 40.5M/170M [00:00<00:01, 114MB/s]
+ 31%|### | 52.4M/170M [00:00<00:01, 109MB/s]
+ 37%|###7 | 63.3M/170M [00:00<00:01, 110MB/s]
+ 44%|####3 | 74.2M/170M [00:00<00:01, 95.0MB/s]
+ 52%|#####1 | 87.6M/170M [00:00<00:00, 107MB/s]
+ 58%|#####7 | 98.5M/170M [00:01<00:00, 98.8MB/s]
+ 65%|######4 | 110M/170M [00:01<00:00, 106MB/s]
+ 71%|#######1 | 121M/170M [00:01<00:00, 98.3MB/s]
+ 78%|#######8 | 133M/170M [00:01<00:00, 105MB/s]
+ 84%|########4 | 143M/170M [00:01<00:00, 96.6MB/s]
+ 90%|########9 | 152M/170M [00:01<00:00, 71.8MB/s]
+ 96%|#########6| 164M/170M [00:01<00:00, 82.2MB/s]
+100%|##########| 170M/170M [00:01<00:00, 96.2MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: 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)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: 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=& [...]
@@ -567,7 +565,7 @@ 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 12.882 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.144 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 7526b35897..d7939229a5 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ training. Other models require a full post training calibration.</p>
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]
- 68%|######8 | 9.27M/13.6M [00:00<00:00, 97.2MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 121MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 65.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 94.0MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ 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)
- 90.3318 90.2340 94.1975 90.0638 0.4280
+ 90.1726 90.1287 91.4865 89.8042 0.2651
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.008 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.174 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 7be328ea77..c0e6131665 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ 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)
- 121.2613 121.2022 126.9510 120.4900 0.6470
+ 119.6057 119.6744 122.6713 117.5132 1.1431
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ 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 30.667 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.138 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 1561e629a8..63c9ef6cb5 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ 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 37.991 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.101 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 222e9b9b08..794bd93856 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,25 +462,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 3%|2 | 3957/132723 [00:00<00:03, 39563.91KB/s]
- 9%|8 | 11394/132723 [00:00<00:02, 60027.13KB/s]
- 13%|#3 | 17397/132723 [00:00<00:04, 23120.07KB/s]
- 19%|#8 | 24693/132723 [00:00<00:03, 33125.10KB/s]
- 24%|##4 | 32474/132723 [00:00<00:02, 43081.22KB/s]
- 29%|##9 | 38619/132723 [00:00<00:02, 46530.91KB/s]
- 34%|###4 | 45342/132723 [00:01<00:01, 51756.27KB/s]
- 39%|###8 | 51562/132723 [00:01<00:01, 50128.93KB/s]
- 43%|####3 | 57290/132723 [00:01<00:01, 41833.95KB/s]
- 49%|####9 | 65345/132723 [00:01<00:01, 50697.51KB/s]
- 54%|#####3 | 71192/132723 [00:01<00:01, 52193.65KB/s]
- 60%|#####9 | 79119/132723 [00:01<00:00, 59201.83KB/s]
- 66%|######5 | 87005/132723 [00:01<00:00, 64507.84KB/s]
- 71%|#######1 | 94894/132723 [00:01<00:00, 68508.63KB/s]
- 78%|#######7 | 102863/132723 [00:01<00:00, 71680.20KB/s]
- 83%|########3 | 110774/132723 [00:02<00:00, 73824.55KB/s]
- 89%|########9 | 118749/132723 [00:02<00:00, 75553.05KB/s]
- 95%|#########5| 126713/132723 [00:02<00:00, 76753.41KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 56152.71KB/s]
+ 3%|2 | 3729/132723 [00:00<00:03, 37047.75KB/s]
+ 8%|8 | 10867/132723 [00:00<00:02, 57185.15KB/s]
+ 15%|#4 | 19669/132723 [00:00<00:01, 71242.63KB/s]
+ 21%|##1 | 28489/132723 [00:00<00:01, 77928.97KB/s]
+ 28%|##8 | 37290/132723 [00:00<00:01, 81558.59KB/s]
+ 35%|###4 | 46011/132723 [00:00<00:01, 83477.59KB/s]
+ 41%|####1 | 54836/132723 [00:00<00:00, 85035.97KB/s]
+ 48%|####8 | 63713/132723 [00:00<00:00, 86212.24KB/s]
+ 55%|#####4 | 72524/132723 [00:00<00:00, 86802.74KB/s]
+ 61%|######1 | 81313/132723 [00:01<00:00, 87134.58KB/s]
+ 68%|######7 | 90118/132723 [00:01<00:00, 87410.45KB/s]
+ 75%|#######4 | 98918/132723 [00:01<00:00, 87587.89KB/s]
+ 81%|########1 | 107737/132723 [00:01<00:00, 87766.49KB/s]
+ 88%|########7 | 116544/132723 [00:01<00:00, 87856.22KB/s]
+ 94%|#########4| 125330/132723 [00:01<00:00, 87659.40KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 83609.22KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -519,7 +516,7 @@ 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> ( 3 minutes 7.561 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> ( 3 minutes 3.922 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 7ddbc7ae9e..74aa10d554 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:53.329</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:31.995</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</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>03:12.882</p></td>
+<td><p>03:11.144</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>03:07.561</p></td>
+<td><p>03:03.922</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>02:30.667</p></td>
+<td><p>02:28.138</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>01:37.991</p></td>
+<td><p>01:24.101</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>01:06.008</p></td>
+<td><p>01:05.174</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:51.256</p></td>
+<td><p>00:53.813</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:36.091</p></td>
+<td><p>00:35.327</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:25.585</p></td>
+<td><p>00:25.391</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:25.282</p></td>
+<td><p>00:24.980</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index e20c5cf007..6b521d0b8d 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ 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.zip22ca0192-9653-421e-83ef-25fa12f6fcbd 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.zipe1634964-83b0-4fbc-acd1-a34b56eb4df6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 57516ed7f8..6e7b893bda 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.110</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.745</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:43.678</p></td>
+<td><p>00:43.370</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>00:02.392</p></td>
+<td><p>00:02.359</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>00:01.032</p></td>
+<td><p>00:01.009</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 77d0d246c8..c8a38a8da2 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ 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: 7127us [7127us] (46.33%; 46.33%)
-FoldScaleAxis: 8256us [6us] (53.67%; 53.67%)
- FoldConstant: 8249us [1714us] (53.63%; 99.92%)
- InferType: 6535us [6535us] (42.49%; 79.22%)
+InferType: 7046us [7046us] (46.17%; 46.17%)
+FoldScaleAxis: 8216us [6us] (53.83%; 53.83%)
+ FoldConstant: 8210us [1682us] (53.79%; 99.92%)
+ InferType: 6528us [6528us] (42.77%; 79.51%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ 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: 6581us [6581us] (45.03%; 45.03%)
-FoldScaleAxis: 8034us [5us] (54.97%; 54.97%)
- FoldConstant: 8030us [1682us] (54.94%; 99.94%)
- InferType: 6348us [6348us] (43.43%; 79.05%)
+InferType: 6588us [6588us] (45.25%; 45.25%)
+FoldScaleAxis: 7970us [5us] (54.75%; 54.75%)
+ FoldConstant: 7965us [1671us] (54.72%; 99.94%)
+ InferType: 6295us [6295us] (43.24%; 79.02%)
</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 8ed9166a77..70b4ebf9f2 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ 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: 38.307327 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.216766 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 7d69fc5c6c..151b319700 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ 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: 13.366374 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.589751 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 8258e8c31e..26ab3b88b2 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ 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: 0.019067
-Baseline: 3.239156
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018491
+Baseline: 3.344994
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ 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: 0.306602
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.293475
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ 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: 0.334659
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337800
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ 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: 0.116172
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115333
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ 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: 0.109575
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109859
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ 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: 0.110681
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110724
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ 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: 0.147055
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146467
</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 59f871e993..8a5b155715 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.693</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.562</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</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>00:31.897</p></td>
+<td><p>00:31.977</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>00:01.621</p></td>
+<td><p>00:01.510</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>00:01.175</p></td>
+<td><p>00:01.075</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 f585d78f48..ff719b2789 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:11.195</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>08:56.971</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</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>05:34.925</p></td>
+<td><p>05:33.672</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>01:32.010</p></td>
+<td><p>01:30.835</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>01:02.237</p></td>
+<td><p>01:01.298</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>00:38.860</p></td>
+<td><p>00:28.118</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:12.034</p></td>
+<td><p>00:11.991</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:11.128</p></td>
+<td><p>00:11.056</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 0d20e4aaa2..b667865732 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
@@ -503,1346 +503,482 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), 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" = 32 {
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 5), 27)) && (floormod((threadIdx.x_1 + 5), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 10), 27)) && (floormod((threadIdx.x_1 + 10), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 5), 9)) && (floormod((threadIdx.x_1 + 15), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormo [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 20), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + fl [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 25), 27)) && (floormod((threadIdx.x_1 + 25), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 27), 3)*7)) + floormod(blockIdx.x, 7)) + fl [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else((((threadIdx.x_1 < 21) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + ((floordiv(threadIdx.x_1, 3) + 1)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.out [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data_3[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + (floordiv((threadIdx.x_2 + 32), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 64), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 96), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 128), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 160), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 192), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 18432)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 320), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 384), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 416), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 480), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 512), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 544)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 544), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 608)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 608), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 640), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 704), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 736)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 736), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 768), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 800)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 800), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 832), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 864)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 55296)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 928)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 928), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 960), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 992)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 992), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1024), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1056), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1088), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1184), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1216), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1248), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1312), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1344), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1376), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1408), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 92160)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1472), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1504), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1536), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1568), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1600), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1632), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1664), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1696), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1760), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1792), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1824), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1856), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1888), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1920), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 1984), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2048), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2080), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2112), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2144), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2176), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2208), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2240), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2272), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2336), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2368), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2400), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2432), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2464), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2496), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2528), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 165888)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2624), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2656), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2688), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2720), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2752), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2784), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2816), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2848), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2912), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2944), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 2976), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3008), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3040), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3072), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3104), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3136), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 202752)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3200), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3232), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3264), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3296), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3328), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3360), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3424), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3488), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3520), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3552), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3584), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3648), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3680), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3712), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 239616)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3776), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3808), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3840), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3872), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3904), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3936), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 3968), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4000), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4096), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4128), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4160), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4192), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4224), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4256), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4288), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel_3[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 276480)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4352), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4384), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4416), 72)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4480), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4512), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4544), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
- kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel_3[(((((floordiv(blockIdx.x, 7)*294912) + (floordiv((threadIdx.x_2 + 4576), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 143)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*144)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 72)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 73)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 74)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 75)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 76)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 77)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 78)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 79)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 80)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 81)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 82)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 83)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 84)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 85)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 86)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 87)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 88)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 89)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 90)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 91)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 92)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 93)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 94)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 95)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 96)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 97)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 98)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 99)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 100)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 101)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 102)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 103)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 104)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 105)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 106)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 107)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 108)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 109)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 110)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 111)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 112)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 113)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 114)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 115)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 116)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 117)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 118)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 119)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 120)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 49)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 121)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 50)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 122)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 51)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 123)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 52)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 124)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 53)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 125)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 54)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 126)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 55)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 127)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 56)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 128)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 57)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 129)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 58)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 130)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 59)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 131)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 60)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 132)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 61)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 133)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 62)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 134)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 63)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 135)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 64)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 136)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 65)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 137)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 66)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 138)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 67)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 139)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 68)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 140)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 69)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 141)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 70)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 142)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 71)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 143)]))
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ for (i3.inner: int32, 0, 7) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias_3: Buffer(bias_2, float32, [512], [])[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -1880,7 +1016,7 @@ 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: 0.290 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.361 ms
</pre></div>
</div>
</div>
@@ -1909,35 +1045,35 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-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=32)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_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=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_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_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_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=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_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=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_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)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
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=7)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
@@ -1958,14 +1094,14 @@ 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=32)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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=4)
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=32)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
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", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1983,1192 +1119,429 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[216];
- __shared__ float kernel_shared[4608];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((3 <= ((((int)threadIdx.x) + 5) % 27)) && (((((int)threadIdx.x) + 5) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % [...]
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((3 <= ((((int)threadIdx.x) + 10) % 27)) && (((((int)threadIdx.x) + 10) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
- pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= (((((int)threadIdx.x) / 3) + 5) % 9)) && (((((int)threadIdx.x) + 15) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 5) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0 [...]
- pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
- pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((3 <= ((((int)threadIdx.x) + 25) % 27)) && (((((int)threadIdx.x) + 25) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
- if (((int)threadIdx.x) < 24) {
- pad_temp_shared[(((int)threadIdx.x) + 192)] = ((((((int)threadIdx.x) < 21) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 1)] : 0.000000e+00f);
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 96) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 160) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 18432)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 608) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 800) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 55296)];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1056) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1184) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1312) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1376) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 92160)];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1760) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1824) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1888) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2336) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2528) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 165888)];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2720) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2976) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3040) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3104) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 202752)];
- kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3488) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3552) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3616) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3680) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 239616)];
- kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3872) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4064) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 276480)];
- kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[((((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4576) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 144)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -3206,7 +1579,7 @@ 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> ( 5 minutes 34.925 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 33.672 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 eb78799392..adbd688cfa 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ 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)
- 7.8180 7.8184 7.8226 7.8130 0.0039
+ 7.8636 7.8653 7.8763 7.8493 0.0111
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ 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 2.237 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.298 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/eafe360d52540634c9eea0fa89e804bd/tune_network_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_network_cuda.py</span></code></a></p>
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 aa351c0756..a215a77af4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ 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)
- 751.4137 751.6945 751.9176 750.6291 0.5623
+ 752.8061 751.9334 756.0780 750.4068 2.3961
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ 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 32.010 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.835 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 21aad77a85..7a91ba4c76 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,13 +632,13 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 16) {
let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
{
- compute_4: Buffer(compute_3, float32, [256], [])[cse_var_1] = 0f32
+ compute_4: Buffer(compute_3, float32, [512], [])[cse_var_1] = 0f32
compute_4[(cse_var_1 + 1)] = 0f32
compute_4[(cse_var_1 + 2)] = 0f32
compute_4[(cse_var_1 + 3)] = 0f32
@@ -657,11 +657,11 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_2 + 1)] - placeholder_15[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
+ for (i.inner: int32, 0, 16) {
let cse_var_21: int32 = (elem_idx*16)
let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256))
+ let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256))
... 3632 lines suppressed ...