You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/08/18 11:53:29 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@436c17f88527406fa1b014b2431609aa217dee48)
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 4f9c64e18 deploying docs (apache/tvm@436c17f88527406fa1b014b2431609aa217dee48)
4f9c64e18 is described below
commit 4f9c64e189b38a39816366d426a1c41d36578f84
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Aug 18 11:53:23 2022 +0000
deploying docs (apache/tvm@436c17f88527406fa1b014b2431609aa217dee48)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../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 | 3155 ++++++++++++++++----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 223 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 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 | 20 +-
.../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_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 12 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 52 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../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 | 3155 ++++++++++++++++----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 223 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
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 | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 20 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
121 files changed, 5922 insertions(+), 2481 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 3af1e4e23..96b272556 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.454 seconds)
+ **Total running time of the script:** ( 1 minutes 6.946 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 3c927d48e..9a267035d 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.zip06a98982-c9e6-43fc-89d2-da8efff4985e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipdc090bfc-8f1f-4fd9-a028-634e5a031055 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 d55a63918..568780a24 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 57.4MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 48.3MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 49.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 56.3MB/s]
90%|######### | 37.5M/41.5M [00:00<00:00, 48.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 29.0MB/s]
22%|##1 | 9.10M/41.5M [00:00<00:01, 26.7MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 32.8MB/s]
42%|####2 | 17.5M/41.5M [00:00<00:00, 32.4MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 36.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 44.6MB/s]
87%|########7 | 36.3M/41.5M [00:01<00:00, 33.1MB/s]
96%|#########5| 39.8M/41.5M [00:01<00:00, 31.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 33.1MB/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 77d260b45..e5a1af315 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
16%|#6 | 7.32M/44.7M [00:00<00:00, 72.7MB/s]
32%|###1 | 14.3M/44.7M [00:00<00:00, 72.4MB/s]
47%|####7 | 21.2M/44.7M [00:00<00:00, 46.0MB/s]
59%|#####8 | 26.3M/44.7M [00:00<00:00, 44.3MB/s]
69%|######9 | 31.0M/44.7M [00:00<00:00, 44.3MB/s]
83%|########3 | 37.1M/44.7M [00:00<00:00, 49.6MB/s]
96%|#########6| 42.9M/44.7M [00:00<00:00, 52.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 50.4MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
20%|## | 9.06M/44.7M [00:00<00:00, 95.0MB/s]
59%|#####8 | 26.1M/44.7M [00:00<00:00, 144MB/s]
98%|#########8| 43.9M/44.7M [00:00<00:00, 163MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 154MB/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 5793eecb9..b1d873894 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.151 seconds)
+ **Total running time of the script:** ( 1 minutes 1.628 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 5d7d19da0..18fc6ce1c 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
=================
-**05:06.761** total execution time for **how_to_compile_models** files:
+**05:07.104** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:05.454 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.946 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.151 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.628 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.273 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.336 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:29.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.349 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.040 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.938 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.859 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.010 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.715 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.218 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.275 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.877 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.558 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.276 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.398 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 93146204f..6493bf628 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1612 16.1079 16.8688 15.8993 0.2720
+ 16.3583 16.1126 17.2927 15.8793 0.4711
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 8498acc29..a06ef4180 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -123,7 +123,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
7%|6 | 11.5M/170M [00:00<00:01, 121MB/s]
17%|#7 | 29.7M/170M [00:00<00:00, 162MB/s]
28%|##8 | 47.9M/170M [00:00<00:00, 175MB/s]
39%|###8 | 66.2M/170M [00:00<00:00, 181MB/s]
50%|####9 | 84.4M/170M [00:00<00:00, 185MB/s]
60%|###### | 102M/170M [00:00<00:00, 187MB/s]
71%|####### | 121M/170M [00:00<00:00, 187MB/s]
82%|########1 | 139M/170M [00:00<00:00, 188MB/s]
92%|#########2| 157M/170M [00:00<00:00, 189MB/s]
100%|##########| 170M/170M [00:00<00:00, 183MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.25M/170M [00:00<00:03, 44.5MB/s]
5%|5 | 8.69M/170M [00:00<00:03, 45.5MB/s]
8%|7 | 13.0M/170M [00:00<00:04, 36.3MB/s]
10%|9 | 16.7M/170M [00:00<00:06, 25.1MB/s]
12%|#1 | 20.2M/170M [00:00<00:05, 28.0MB/s]
14%|#4 | 24.4M/170M [00:00<00:04, 31.7MB/s]
16%|#6 | 27.7M/170M [00:00<00:04, 30.1MB/s]
19%|#9 | 32.5M/170M [00:01<00:04, 35.4MB/s]
22%|##2 | 37.7M/170M [00:01<00:03, 40.4MB/s]
25%|##4 | 41.8M/170M [00:01<00:03, 39.0MB/s]
27%|##7 | 46.5M/170M [00:01<00:03, 41.6MB/s]
30%|##9 | 50.6M/170M [00:01<00:03, 37.9MB/s]
34%|###3 | 57.0M/170M [00:01<00:02, 45.7MB/s]
36%|###6 | 61.6M/170M [00:01<00:02, 39.0MB/s]
39%|###8 | 66.2M/170M [00:01<00:02, 41.2MB/s]
41%|####1 | 70.4M/170M [00:01<00:02, 39.6MB/s]
44%|####3 | 74.3M/170M [00:02<00:02, 36.6MB/
s]
47%|####6 | 79.8M/170M [00:02<00:02, 41.8MB/s]
50%|####9 | 84.8M/170M [00:02<00:02, 44.3MB/s]
52%|#####2 | 89.1M/170M [00:02<00:02, 41.1MB/s]
56%|#####5 | 94.6M/170M [00:02<00:01, 45.5MB/s]
58%|#####8 | 99.1M/170M [00:02<00:01, 41.7MB/s]
61%|###### | 103M/170M [00:02<00:02, 32.1MB/s]
63%|######3 | 107M/170M [00:03<00:01, 34.2MB/s]
65%|######5 | 111M/170M [00:03<00:01, 32.5MB/s]
68%|######7 | 115M/170M [00:03<00:01, 35.8MB/s]
70%|####### | 119M/170M [00:03<00:01, 35.0MB/s]
73%|#######2 | 123M/170M [00:03<00:01, 36.1MB/s]
75%|#######4 | 127M/170M [00:03<00:01, 35.7MB/s]
77%|#######7 | 132M/170M [00:03<00:01, 39.8MB/s]
80%|######## | 136M/170M [00:03<00:00, 42.7MB/s]
83%|########2 | 141M/170M [00:03<00:00, 43.0MB/s]
85%|########5 | 145M/170M [00:04<00:00, 34.0MB/s]
87%|########7 | 148M/170M [00:04<00:00, 34.4MB/s]
90%|########9 | 152M/170M [00:04<00:00, 36.0MB/s
]
92%|#########2| 157M/170M [00:04<00:00, 38.4MB/s]
95%|#########4| 161M/170M [00:04<00:00, 38.4MB/s]
97%|#########6| 164M/170M [00:04<00:00, 38.8MB/s]
100%|#########9| 169M/170M [00:04<00:00, 40.8MB/s]
100%|##########| 170M/170M [00:04<00:00, 37.7MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 0.327 seconds)
+ **Total running time of the script:** ( 3 minutes 6.314 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 4cb0002e3..93aa479fa 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
11%|#1 | 1.52M/13.6M [00:00<00:00, 15.2MB/s]
29%|##8 | 3.90M/13.6M [00:00<00:00, 20.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 52.1MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
80%|#######9 | 10.8M/13.6M [00:00<00:00, 114MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 127MB/s]
@@ -412,7 +412,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.6549 90.6036 97.1303 90.1025 0.6928
+ 90.2902 90.2601 90.6985 90.1629 0.1012
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.859 seconds)
+ **Total running time of the script:** ( 1 minutes 10.504 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 064a6a72a..9e7a0147c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -439,7 +439,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.0987 120.9695 125.6456 120.1847 0.7752
+ 120.0597 119.9950 122.0563 119.1450 0.4472
@@ -476,7 +476,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 54.936 seconds)
+ **Total running time of the script:** ( 1 minutes 53.582 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 8e01ae866..2453c5394 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 39.834 seconds)
+ **Total running time of the script:** ( 1 minutes 41.219 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 2d27d2a60..0f02db00d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6184/132723 [00:00<00:02, 61830.18KB/s]
11%|# | 14517/132723 [00:00<00:01, 74471.65KB/s]
17%|#7 | 22775/132723 [00:00<00:01, 78170.38KB/s]
23%|##3 | 31073/132723 [00:00<00:01, 80063.79KB/s]
30%|##9 | 39373/132723 [00:00<00:01, 81118.43KB/s]
36%|###5 | 47741/132723 [00:00<00:01, 81983.33KB/s]
42%|####2 | 56053/132723 [00:00<00:00, 82353.45KB/s]
49%|####8 | 64465/132723 [00:00<00:00, 82912.60KB/s]
55%|#####4 | 72850/132723 [00:00<00:00, 83203.10KB/s]
61%|######1 | 81297/132723 [00:01<00:00, 83592.74KB/s]
68%|######7 | 89657/132723 [00:01<00:00, 80535.73KB/s]
74%|#######3 | 98033/132723 [00:01<00:00, 81489.30KB/s]
80%|######## | 106201/132723 [00:01<00:00, 63610.46KB/s]
86%|########6 | 114584/132723 [00:01<00:00, 68641.87KB/s]
92%|#########1| 121977/132723 [00:01<00:00, 62447.86KB/s]
98%|########
#7| 129841/132723 [00:02<00:00, 40230.83KB/s]
100%|##########| 132723/132723 [00:02<00:00, 62190.36KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
3%|2 | 3969/132723 [00:00<00:03, 39680.39KB/s]
9%|8 | 11597/132723 [00:00<00:01, 61205.74KB/s]
14%|#4 | 19240/132723 [00:00<00:01, 68153.74KB/s]
20%|## | 26830/132723 [00:00<00:01, 71207.53KB/s]
26%|##5 | 34433/132723 [00:00<00:01, 72944.43KB/s]
32%|###1 | 42094/132723 [00:00<00:01, 74188.97KB/s]
37%|###7 | 49757/132723 [00:00<00:01, 74984.46KB/s]
43%|####3 | 57423/132723 [00:00<00:00, 75514.02KB/s]
49%|####9 | 65158/132723 [00:00<00:00, 76085.17KB/s]
55%|#####4 | 72864/132723 [00:01<00:00, 76384.94KB/s]
61%|###### | 80613/132723 [00:01<00:00, 76720.91KB/s]
67%|######6 | 88321/132723 [00:01<00:00, 76828.21KB/s]
72%|#######2 | 96012/132723 [00:01<00:00, 76851.73KB/s]
78%|#######8 | 103698/132723 [00:01<00:00, 75907.90KB/s]
84%|########3 | 111401/132723 [00:01<00:00, 76239.91KB/s]
90%|########9
| 119031/132723 [00:01<00:00, 76255.19KB/s]
95%|#########5| 126715/132723 [00:01<00:00, 76422.18KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72400.58KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 35.576 seconds)
+ **Total running time of the script:** ( 2 minutes 38.575 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 dc596d6d4..71eff99b1 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**11:36.474** total execution time for **how_to_deploy_models** files:
+**11:45.053** 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``) | 03:00.327 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:06.314 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:35.576 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:38.575 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:54.936 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.582 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:39.834 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:41.219 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.859 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:10.504 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.509 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:22.341 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.164 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.004 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 96dffb297..7c14d7939 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -476,7 +476,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd9bb0f57-139c-4ef3-95c3-ea24aa33efc3 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf9aa5403-43ac-4905-8ad5-f1c910eb9971 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 1a159f12e..d880e036c 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
=================
-**00:40.890** total execution time for **how_to_extend_tvm** files:
+**00:41.537** 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``) | 00:37.641 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.322 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.270 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.973 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.938 | 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 a89d0f64e..84215f7e4 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: 6953us [6953us] (46.50%; 46.50%)
- FoldScaleAxis: 8000us [5us] (53.50%; 53.50%)
- FoldConstant: 7995us [1673us] (53.47%; 99.94%)
- InferType: 6322us [6322us] (42.28%; 79.07%)
+ InferType: 6740us [6740us] (46.32%; 46.32%)
+ FoldScaleAxis: 7812us [5us] (53.68%; 53.68%)
+ FoldConstant: 7806us [1629us] (53.64%; 99.93%)
+ InferType: 6177us [6177us] (42.45%; 79.13%)
@@ -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: 6481us [6481us] (44.83%; 44.83%)
- FoldScaleAxis: 7978us [5us] (55.17%; 55.17%)
- FoldConstant: 7973us [1670us] (55.14%; 99.94%)
- InferType: 6303us [6303us] (43.59%; 79.06%)
+ InferType: 6184us [6184us] (42.75%; 42.75%)
+ FoldScaleAxis: 8281us [5us] (57.25%; 57.25%)
+ FoldConstant: 8277us [1775us] (57.22%; 99.94%)
+ InferType: 6502us [6502us] (44.95%; 78.55%)
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 78626184e..f81de16d1 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: 54.232151 ms
+ Convolution: 34.182658 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 ea64a4b4a..f5ac03021 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.857927 ms
+ conv2d with tensor core: 8.292166 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 c30634b2f..1edfb1694 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: 0.019390
- Baseline: 3.444834
+ Numpy running time: 0.019473
+ Baseline: 3.407826
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.305296
+ Opt1: 0.308518
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335842
+ Opt2: 0.340642
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116988
+ Opt3: 0.117791
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110721
+ Opt4: 0.110714
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111310
+ Opt5: 0.110970
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145615
+ Opt6: 0.145490
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 8df3d64a2..90f555250 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
=================
-**00:34.810** total execution time for **how_to_optimize_operators** files:
+**00:34.757** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.457 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.537 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.251 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.229 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.990 | 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 298bd4d7b..f2506a697 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:13.013** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:15.543** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:24.257 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:28.044 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.294 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:23.027 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.555 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.368 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.927 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.462 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.025 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.912 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.954 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.730 | 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 26ee0e0ed..2c01f6bb8 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,12 +240,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [432]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -256,325 +256,1341 @@ cooperative fetching, unrolling and operator fusion.
let cse_var_2: int32 = (rc.outer.outer*784)
let cse_var_1: int32 = (rc.outer.outer*144)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*2)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*2), 81)) && (floormod((threadIdx.x_1*2), 81) < 72)) && (1 <= floormod((threadIdx.x_1*2), 9))) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 81)*49)) + (floordiv(floormod((threadIdx.x_1*2), 81), 9)*7)) + floormod((threadIdx.x_1*2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 1), 81)) && (floormod(((threadIdx.x_1*2) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 9))) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- pad_temp.shared_1[((threadIdx.x_1*2) + 448)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 43), 81)) && (floormod(((threadIdx.x_1*2) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 7), 9))) && (floormod(((threadIdx.x_1*2) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 448), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 43), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 449)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 44), 81)) && (floormod(((threadIdx.x_1*2) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 8), 9))) && (floormod(((threadIdx.x_1*2) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 449), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 44), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- if @tir.likely((threadIdx.x_1 < 200), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 896)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 5), 81)) && (floormod(((threadIdx.x_1*2) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 5), 9))) && (floormod(((threadIdx.x_1*2) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 896), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 200), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 897)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 6), 81)) && (floormod(((threadIdx.x_1*2) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 6), 9))) && (floormod(((threadIdx.x_1*2) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 897), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [432], [], 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[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, [...]
+ 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[(((((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[(((((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)) - 8) [...]
+ 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[(((((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[(((((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[(((((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;
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 1), 9)) && (floormod((threadIdx.x_1 + 3), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 1), 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 + 224)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 8), 27)) && (floormod((threadIdx.x_1 + 8), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 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 + 256)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 13), 27)) && (floormod((threadIdx.x_1 + 13), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 256), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 13), 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 + 288)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 6), 9)) && (floormod((threadIdx.x_1 + 18), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 288), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 6), 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 + 320)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 23), 27)) && (floormod((threadIdx.x_1 + 23), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 320), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 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 + 352)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 1), 27)) && (floormod((threadIdx.x_1 + 1), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 352), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)] [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 384)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 2), 9)) && (floormod((threadIdx.x_1 + 6), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 384), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 2), 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;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 416)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 416), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
}
+ 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[(((floordiv(blockIdx.x, 7)*147456) + 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[((((floordiv(blockIdx.x, 7)*147456) + 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 64), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 96)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 192), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 320), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 384), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 480), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 512), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 608)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 608), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 704), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 768), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 832), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 928), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 960), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 992), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1024), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1056), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 1184)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1184), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1216), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1248), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1376), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1504), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1536), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1600), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1632), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1664), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1696), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 1760)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1760), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1824), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1856), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1888), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1920), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1984), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2048), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2112), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2208), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2272), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 2336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2336), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2368), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2400), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2432), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2496), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2528), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2656), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2720), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2784), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2816), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2848), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 2912)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2944), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2976), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3008), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3040), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3072), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3104), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3200), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3264), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3328), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 3488)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3488), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3520), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3552), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3648), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3680), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3712), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3776), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3840), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3872), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3936), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4000), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 4064)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4096), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4128), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4192), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4224), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4384), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4416), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4512), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[216]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[219]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[219]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[237]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[237]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[240]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[243]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[246]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[246]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[264]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[264]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[267]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[217]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[220]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[220]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[238]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[238]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[241]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[244]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[247]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[247]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[265]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[265]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[268]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[218]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[221]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[221]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[239]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[239]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[242]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[245]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[248]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[248]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[266]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[266]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[269]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[270]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[273]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[273]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[291]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[291]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[294]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[297]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[300]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[300]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[318]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[318]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[321]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[271]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[274]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[274]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[292]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[292]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[295]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[298]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[301]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[301]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[319]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[319]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[322]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[272]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[275]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[275]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[293]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[293]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[296]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[299]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[302]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[302]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[320]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[320]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[323]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[324]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[327]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[327]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[345]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[345]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[348]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[351]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[354]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[354]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[372]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[372]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[375]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[325]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[328]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[328]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[346]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[346]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[349]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[352]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[355]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[355]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[373]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[373]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[376]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[326]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[329]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[329]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[347]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[347]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[350]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[353]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[356]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[356]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[374]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[374]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[377]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[378]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[381]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[381]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[399]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[399]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[402]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[405]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[408]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[408]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[426]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[426]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[429]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[379]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[382]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[382]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[400]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[400]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[403]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[406]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[409]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[409]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[427]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[427]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[430]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[380]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[383]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[383]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[401]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[401]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[404]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[407]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[410]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[410]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[428]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[428]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[431]*kernel.shared_1[((threadIdx.x*144) + 143)]))
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
}
}
@@ -628,7 +1644,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.198 ms
+ Execution time of this operator: 0.215 ms
@@ -682,18 +1698,18 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
- conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+ conv2d_nchw_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=7)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ 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=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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)
@@ -702,9 +1718,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
- compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_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=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
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)
@@ -725,14 +1741,14 @@ 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=224)
+ 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)
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=2)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ 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)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -750,9 +1766,9 @@ 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__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[1296];
+ __shared__ float pad_temp_shared[432];
__shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -763,298 +1779,1183 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[6] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = (((((9 <= ((((int)threadIdx.x) * 2) % 81)) && (((((int)threadIdx.x) * 2) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 81) * 49)) + ((((((int)threadIdx.x) * 2) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((((9 <= (((((int)threadIdx.x) * 2) + 1) % 81)) && ((((((int)threadIdx.x) * 2) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 448)] = (((((9 <= (((((int)threadIdx.x) * 2) + 43) % 81)) && ((((((int)threadIdx.x) * 2) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 448) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 43) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 449)] = (((((9 <= (((((int)threadIdx.x) * 2) + 44) % 81)) && ((((((int)threadIdx.x) * 2) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 449) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 44) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 200) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 896)] = (((((9 <= (((((int)threadIdx.x) * 2) + 5) % 81)) && ((((((int)threadIdx.x) * 2) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 896) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 200) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 897)] = (((((9 <= (((((int)threadIdx.x) * 2) + 6) % 81)) && ((((((int)threadIdx.x) * 2) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 897) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ 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 * 784) + ((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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);
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (((((int)threadIdx.x) / 3) + 1) % 9)) && (((((int)threadIdx.x) + 3) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 1) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((3 <= ((((int)threadIdx.x) + 8) % 27)) && (((((int)threadIdx.x) + 8) % 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 * 784) + (((((int)threadIdx.x) + 224) / 27) * 49)) + ((((((int)threadIdx.x) + 8) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 256)] = (((((3 <= ((((int)threadIdx.x) + 13) % 27)) && (((((int)threadIdx.x) + 13) % 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 * 784) + (((((int)threadIdx.x) + 256) / 27) * 49)) + ((((((int)threadIdx.x) + 13) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 288)] = (((((1 <= (((((int)threadIdx.x) / 3) + 6) % 9)) && (((((int)threadIdx.x) + 18) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 288) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 6) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 320)] = (((((3 <= ((((int)threadIdx.x) + 23) % 27)) && (((((int)threadIdx.x) + 23) % 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 * 784) + (((((int)threadIdx.x) + 320) / 27) * 49)) + ((((((int)threadIdx.x) + 23) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 352)] = (((((3 <= ((((int)threadIdx.x) + 1) % 27)) && (((((int)threadIdx.x) + 1) % 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 * 784) + (((((int)threadIdx.x) + 352) / 27) * 49)) + ((((((int)threadIdx.x) + 1) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 384)] = (((((1 <= (((((int)threadIdx.x) / 3) + 2) % 9)) && (((((int)threadIdx.x) + 6) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 384) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 416)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 416) / 27) * 49)) + (((((int)threadIdx.x) + 11) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1216) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1312) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1376) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1408) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1504) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1600) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1632) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1664) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1696) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1760) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1888) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1984) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2048) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2208) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2272) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2336) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2368) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2432) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2528) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2560) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2656) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2816) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2848) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2944) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2976) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3008) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3040) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3072) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3104) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3200) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3264) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3328) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3392) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3424) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3488) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3520) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3552) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3648) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3680) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3712) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3776) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3872) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3936) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4000) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4096) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4160) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4192) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4288) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4384) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4576) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- }
- }
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[216] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[219] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[219] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[237] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[237] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[240] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[243] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[246] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[246] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[264] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[264] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[267] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[217] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[220] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[220] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[238] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[238] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[241] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[244] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[247] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[247] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[265] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[265] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[268] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[218] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[221] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[221] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[239] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[239] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[242] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[245] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[248] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[248] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[266] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[266] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[269] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[270] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[273] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[273] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[291] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[291] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[294] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[297] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[300] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[300] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[318] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[318] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[321] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[271] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[274] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[274] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[292] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[292] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[295] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[298] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[301] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[301] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[319] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[319] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[322] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[272] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[275] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[275] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[293] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[293] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[296] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[299] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[302] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[302] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[320] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[320] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[323] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[324] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[327] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[327] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[345] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[345] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[348] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[351] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[354] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[354] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[372] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[372] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[375] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[325] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[328] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[328] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[346] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[346] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[349] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[352] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[355] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[355] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[373] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[373] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[376] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[326] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[329] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[329] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[347] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[347] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[350] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[353] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[356] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[356] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[374] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[374] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[377] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[378] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[381] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[381] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[399] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[399] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[402] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[405] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[408] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[408] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[426] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[426] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[429] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[379] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[382] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[382] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[400] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[400] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[403] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[406] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[409] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[409] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[427] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[427] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[430] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[380] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[383] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[383] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[401] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[401] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[404] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[407] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[410] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[410] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[428] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[428] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[431] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
}
@@ -1115,7 +3016,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 24.257 seconds)
+ **Total running time of the script:** ( 3 minutes 28.044 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 a50e7f6a4..4232b4b9c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8389 9.8324 9.8854 9.7990 0.0356
+ 9.9080 9.9079 9.9352 9.8808 0.0222
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 169e68cbe..2d0ae8342 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.8519 755.3273 755.6256 753.6029 0.8916
+ 746.5228 745.6988 748.5021 745.3677 1.4060
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.294 seconds)
+ **Total running time of the script:** ( 1 minutes 23.027 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 7028421c2..094045d99 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -397,217 +397,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_67: int32 = (i.outer.inner*1024)
- let cse_var_66: int32 = (elem_idx*16)
- let cse_var_65: int32 = (cse_var_1 + 99)
- let cse_var_64: int32 = (cse_var_1 + 98)
- let cse_var_63: int32 = (cse_var_1 + 97)
- let cse_var_62: int32 = (cse_var_1 + 96)
- let cse_var_61: int32 = (cse_var_1 + 9)
- let cse_var_60: int32 = (cse_var_1 + 8)
- let cse_var_59: int32 = (cse_var_1 + 79)
- let cse_var_58: int32 = (cse_var_1 + 78)
- let cse_var_57: int32 = (cse_var_1 + 77)
- let cse_var_56: int32 = (cse_var_1 + 76)
- let cse_var_55: int32 = (cse_var_1 + 75)
- let cse_var_54: int32 = (cse_var_1 + 74)
- let cse_var_53: int32 = (cse_var_1 + 73)
- let cse_var_52: int32 = (cse_var_1 + 72)
- let cse_var_51: int32 = (cse_var_1 + 71)
- let cse_var_50: int32 = (cse_var_1 + 70)
- let cse_var_49: int32 = (cse_var_1 + 7)
- let cse_var_48: int32 = (cse_var_1 + 69)
- let cse_var_47: int32 = (cse_var_1 + 68)
- let cse_var_46: int32 = (cse_var_1 + 67)
- let cse_var_45: int32 = (cse_var_1 + 66)
- let cse_var_44: int32 = (cse_var_1 + 65)
- let cse_var_43: int32 = (cse_var_1 + 64)
- let cse_var_42: int32 = (cse_var_1 + 6)
- let cse_var_41: int32 = (cse_var_1 + 5)
- let cse_var_40: int32 = (cse_var_1 + 47)
- let cse_var_39: int32 = (cse_var_1 + 46)
- let cse_var_38: int32 = (cse_var_1 + 45)
- let cse_var_37: int32 = (cse_var_1 + 44)
- let cse_var_36: int32 = (cse_var_1 + 43)
- let cse_var_35: int32 = (cse_var_1 + 42)
- let cse_var_34: int32 = (cse_var_1 + 41)
- let cse_var_33: int32 = (cse_var_1 + 40)
- let cse_var_32: int32 = (cse_var_1 + 4)
- let cse_var_31: int32 = (cse_var_1 + 39)
- let cse_var_30: int32 = (cse_var_1 + 38)
- let cse_var_29: int32 = (cse_var_1 + 37)
- let cse_var_28: int32 = (cse_var_1 + 36)
- let cse_var_27: int32 = (cse_var_1 + 35)
- let cse_var_26: int32 = (cse_var_1 + 34)
- let cse_var_25: int32 = (cse_var_1 + 33)
- let cse_var_24: int32 = (cse_var_1 + 32)
- let cse_var_23: int32 = (cse_var_1 + 3)
- let cse_var_22: int32 = (cse_var_1 + 2)
- let cse_var_21: int32 = (cse_var_1 + 15)
- let cse_var_20: int32 = (cse_var_1 + 14)
- let cse_var_19: int32 = (cse_var_1 + 13)
- let cse_var_18: int32 = (cse_var_1 + 12)
- let cse_var_17: int32 = (cse_var_1 + 111)
- let cse_var_16: int32 = (cse_var_1 + 110)
- let cse_var_15: int32 = (cse_var_1 + 11)
- let cse_var_14: int32 = (cse_var_1 + 109)
- let cse_var_13: int32 = (cse_var_1 + 108)
- let cse_var_12: int32 = (cse_var_1 + 107)
- let cse_var_11: int32 = (cse_var_1 + 106)
- let cse_var_10: int32 = (cse_var_1 + 105)
- let cse_var_9: int32 = (cse_var_1 + 104)
- let cse_var_8: int32 = (cse_var_1 + 103)
- let cse_var_7: int32 = (cse_var_1 + 102)
- let cse_var_6: int32 = (cse_var_1 + 101)
- let cse_var_5: int32 = (cse_var_1 + 100)
- let cse_var_4: int32 = (cse_var_1 + 10)
- let cse_var_3: int32 = (cse_var_1 + 1)
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ for (i.inner.init: int32, 0, 2) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*64) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 2) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*64) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_68: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -663,7 +476,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 3.019 ms
+ Execution time of this operator: 2.117 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 dc4290f2d..319d270db 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:46.108** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.734** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.073 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.697 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index a8cd1559e..1767f6d63 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 80.76/80.76 result: MeasureResult(costs=(0.0028664421142857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8323888778686523, timestamp=1660816877.334716) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/80.76 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 220.36/220.36 result: MeasureResult(costs=(0.0010505666896551723,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9906036853790283, timestamp=1660816717.9250998) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/220.36 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.97/260.97 result: MeasureResult(costs=(0.0008870664917127072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.728985071182251, timestamp=1660816878.2587764) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 261.47/261.47 result: MeasureResult(costs=(0.0008853753093922652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7667784690856934, timestamp=1660816718.856316) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.31/260.97 result: MeasureResult(costs=(0.0436249185,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8379912376403809, timestamp=1660816882.8576086) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.34/260.97 result: MeasureResult(costs=(0.06930364874999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.6043665409088135, timestamp=1660816884.0969527) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.36/261.47 result: MeasureResult(costs=(0.043183570500000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8371973037719727, timestamp=1660816723.4216356) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.36/261.47 result: MeasureResult(costs=(0.068981317,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5557684898376465, timestamp=1660816724.6612272) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.13/260.97 result: MeasureResult(costs=(0.008230546714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2766973972320557, timestamp=1660816895.1346583) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 27.59/261.47 result: MeasureResult(costs=(0.008389330642857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2751076221466064, timestamp=1660816735.6851811) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001270
+ Time cost of this operator: 0.001217
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 d0303d058..3aedab2fa 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 309.3 98.725 (1, 2, 10, 10, 3) 2 1 [309.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.031 0.967 (1, 6, 10, 10) 1 1 [3.031]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.307 (1, 1, 10, 10, 3) 1 1 [0.962]
- Total_time - 313.293 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.733 (1, 2, 10, 10, 3) 2 1 [310.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.959 (1, 6, 10, 10) 1 1 [3.017]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.971 0.308 (1, 1, 10, 10, 3) 1 1 [0.971]
+ Total_time - 314.688 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 119.8 97.748 (1, 6, 10, 10, 1) 2 1 [119.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.807 1.474 (1, 6, 10, 10) 1 1 [1.807]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.778 (1, 1, 10, 10, 3) 1 1 [0.953]
- Total_time - 122.56 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 130.0 97.897 (1, 6, 10, 10, 1) 2 1 [130.0]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.808 1.362 (1, 6, 10, 10) 1 1 [1.808]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.741 (1, 1, 10, 10, 3) 1 1 [0.984]
+ Total_time - 132.793 - - - - -
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 3dbe53477..edbcb0448 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/tmpnxg7j5g1/images/random'
+ '/tmp/tmpxmt6h_yv/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpnxg7j5g1/images/target contains 8144 images
- /tmp/tmpnxg7j5g1/images/random contains 5000 images
+ /tmp/tmpxmt6h_yv/images/target contains 8144 images
+ /tmp/tmpxmt6h_yv/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2389 - accuracy: 0.9192 - val_loss: 0.1476 - val_accuracy: 0.9585
+ 328/328 - 55s - loss: 0.2318 - accuracy: 0.9206 - val_loss: 0.1407 - val_accuracy: 0.9573
Epoch 2/3
- 328/328 - 53s - loss: 0.1039 - accuracy: 0.9615 - val_loss: 0.1319 - val_accuracy: 0.9577
+ 328/328 - 52s - loss: 0.1050 - accuracy: 0.9612 - val_loss: 0.1237 - val_accuracy: 0.9645
Epoch 3/3
- 328/328 - 52s - loss: 0.0653 - accuracy: 0.9752 - val_loss: 0.1104 - val_accuracy: 0.9622
+ 328/328 - 52s - loss: 0.0658 - accuracy: 0.9755 - val_loss: 0.1786 - val_accuracy: 0.9532
- <keras.callbacks.History object at 0x7f488894af50>
+ <keras.callbacks.History object at 0x7f5dbc73e610>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 39.005 seconds)
+ **Total running time of the script:** ( 6 minutes 9.377 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 081a8e7b7..8113747ec 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**06:32.704** total execution time for **how_to_work_with_microtvm** files:
+**07:02.215** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:39.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 06:09.377 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.652 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.026 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.641 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.518 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.404 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.293 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index d3cdcad17..023708c9c 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
=================
-**00:41.121** total execution time for **how_to_work_with_relay** files:
+**00:38.456** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:30.818 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:08.629 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:06.312 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.318 | 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 37fdf97aa..768ae925c 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 0x7f4888fa8200>
+ <function my_cuda_math_rule at 0x7f5d2b47e0e0>
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 fb0ff90f5..b5f34bcc6 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
=================
-**00:04.122** total execution time for **how_to_work_with_schedules** files:
+**00:03.928** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.911 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.818 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.976 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.919 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.530 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.513 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.520 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.495 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.041 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 24de495a4..f531a2112 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpmz9u91pi/input0.cc'\nsource_filename = \"/tmp/tmpmz9u91pi/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/tmpv70ud6xb/input0.cc'\nsource_filename = \"/tmp/tmpv70ud6xb/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 f505fa555..730d903e8 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
=================
-**00:21.881** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.856** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.875 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.849 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index afd045054..58e79fdfa 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.51s!
+ resnet18_v1 inference graph built in 23.42s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index b3b676352..6eaa43e4f 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.63s!
+ yolov3-tiny inference graph built in 16.27s!
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 354b983c1..ec5e41a71 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
=================
-**01:32.755** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.997** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.226 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.371 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.529 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.626 | 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 de674785d..a7c351cbb 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
=================
-**00:03.263** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.246** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.852 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.859 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.411 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.387 | 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 c448dba27..72846c388 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
=================
-**00:00.745** total execution time for **topic_vta_tutorials** files:
+**00:00.683** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.364 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.346 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.319 | 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 acadf5937..d8d2ff6ce 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -205,13 +205,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- *E
-
-
@@ -335,7 +328,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.065 ms
+ Execution time of this operator: 93.376 ms
@@ -453,7 +446,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.821 seconds)
+ **Total running time of the script:** ( 1 minutes 4.819 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 d1ded5a20..26350c6be 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.50/9.50 result: MeasureResult(costs=(0.028241509600000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5861542224884033, timestamp=1660815635.961635) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.97/9.50 result: MeasureResult(costs=(0.09026057540000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6037747859954834, timestamp=1660815638.1141913) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.86/11.86 result: MeasureResult(costs=(0.0226353608,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.585747480392456, timestamp=1660815638.6785924) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.86 result: MeasureResult(costs=(0.144940171,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.43800687789917, timestamp=1660815641.6969814) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.65/11.86 result: MeasureResult(costs=(0.0735951458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3145930767059326, timestamp=1660815643.1409006) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.81/11.86 result: MeasureResult(costs=(0.1482625702,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5340895652770996, timestamp=1660815645.717855) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.86/11.86 result: MeasureResult(costs=(0.31237005959999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.1105194091796875, timestamp=1660815651.411121) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.63/11.86 result: MeasureResult(costs=(0.0252465704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5490591526031494, timestamp=1660815651.9782858) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.92/11.86 result: MeasureResult(costs=(0.1400208594,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3601667881011963, timestamp=1660815654.458112) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.60/11.86 result: MeasureResult(costs=(0.103265249,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7657864093780518, timestamp=1660815656.2725596) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.87/9.87 result: MeasureResult(costs=(0.027194919599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5733973979949951, timestamp=1660815474.1244102) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.67/9.87 result: MeasureResult(costs=(0.10051182480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7581737041473389, timestamp=1660815475.8960972) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.87/11.87 result: MeasureResult(costs=(0.022616575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5648493766784668, timestamp=1660815476.9559824) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.63/11.87 result: MeasureResult(costs=(0.1643231462,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.745412588119507, timestamp=1660815479.7494464) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.64/11.87 result: MeasureResult(costs=(0.0737005274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3222377300262451, timestamp=1660815481.200415) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.88/11.87 result: MeasureResult(costs=(0.1426855688,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.408039093017578, timestamp=1660815484.1799722) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.83/11.87 result: MeasureResult(costs=(0.3231522946,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.288594961166382, timestamp=1660815490.0480692) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.91/11.87 result: MeasureResult(costs=(0.0270931286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5993258953094482, timestamp=1660815490.6576333) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.90/11.87 result: MeasureResult(costs=(0.1411253204,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.366215467453003, timestamp=1660815493.1431897) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.61/11.87 result: MeasureResult(costs=(0.1028862274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.751206874847412, timestamp=1660815494.952276) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index abb9df940..db8047fbf 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 496.0577789099989, 'median': 496.2480519999872, 'std': 1.0074012982807468}
+ {'mean': 496.7395671700251, 'median': 496.49149335009497, 'std': 1.2848992267195383}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.43/ 17.43 GFLOPS | Progress: (4/20) | 6.36 s
[Task 1/25] Current/Best: 6.15/ 17.43 GFLOPS | Progress: (8/20) | 9.31 s
[Task 1/25] Current/Best: 11.52/ 22.74 GFLOPS | Progress: (12/20) | 11.75 s
[Task 1/25] Current/Best: 16.81/ 22.82 GFLOPS | Progress: (16/20) | 13.43 s
[Task 1/25] Current/Best: 11.62/ 23.82 GFLOPS | Progress: (20/20) | 15.19 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.23/ 12.96 GFLOPS | Progress: (4/20) | 3.68 s
[Task 2/25] Current/Best: 13.93/ 18.22 GFLOPS | Progress: (8/20) | 5.02 s
[Task 2/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (12/20) | 6.36 s
[Task 2/25] Current/Best: 12.50/ 21.09 GFLOPS | Progress: (16/20) | 7.63 s
[Task 2/25] Current/Best: 19.11/ 21.09 GFLOPS | Progress: (20/20) | 9.25 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.60/ 16.91 GFLOPS | Progress: (8/20) | 7.80 s
[Task 3/25] Current/Best: 14.94/ 16.91 GFLOPS | Progress: (12/20) | 9.53 s
[Task 3/25] Current/Best: 7.20/ 23.71 GFLOPS | Progress: (16/20) | 11.46 s
[Task 3/25] Current/Best: 12.58/ 23.71 GFLOPS | Progress: (20/20) | 16.01 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 20.50 GFLOPS | Progress: (4/20) | 2.43 s
[Task 4/25] Current/Best: 6.84/ 20.50 GFLOPS | Progress: (8/20) | 6.77 s
[Task 4/25] Current/Best: 21.74/ 21.74 GFLOPS | Progress: (12/20) | 11.21 s
[Task 4/25] Current/Best: 16.78/ 21.74 GFLOPS | Progress: (16/20) | 13.45 s
[Task 4/25] Current/Best: 13.43/ 21.74 GFLOPS | Progress: (20/20) | 15.44 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.51/ 10.32 GFLOPS | Progress: (4/20) | 2.62 s
[Task 5/25] Current/Best: 11.80/ 12.73 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 11.35/ 18.20 GFLOPS | Progress: (12/20) | 7.62 s
[Task 5/25] Current/Best: 11.71/ 22.66 GFLOPS | Progress: (16/20) | 9.05 s
[Task 5/25] Current/Best: 12.01/ 22.66 GFLOPS | Progress: (20/20) | 10.90 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.20/ 20.78 GFLOPS | Progress: (4/20) | 3.99 s
[Task 6/25] Current/Best: 18.86/ 20.78 GFLOPS | Progress: (8/20) | 5.76 s
[Task 6/25] Current/Best: 13.22/ 20.78 GFLOPS | Progress: (12/20) | 7.68 s
[Task 6/25] Current/Best: 20.02/ 20.78 GFLOPS | Progress: (16/20) | 9.92 s
[Task 6/25] Current/Best: 3.73/ 20.78 GFLOPS | Progress: (20/20) | 12.43 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.20/ 12.87 GFLOPS | Progress: (4/20) | 3.63 s
[Task 7/25] Current/Best: 20.20/ 21.10 GFLOPS | Progress: (8/20) | 5.14 s
[Task 7/25] Current/Best: 16.12/ 21.10 GFLOPS | Progress: (12/20) | 7.03 s
[Task 7/25] Current/Best: 12.25/ 21.10 GFLOPS | Progress: (16/20) | 9.08 s
[Task 7/25] Current/Best: 6.46/ 21.90 GFLOPS | Progress: (20/20) | 11.53 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.13/ 14.52 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.91/ 14.52 GFLOPS | Progress: (8/20) | 7.63 s
[Task 8/25] Current/Best: 12.40/ 14.52 GFLOPS | Progress: (12/20) | 13.80 s
[Task 8/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (16/20) | 15.88 s
[Task 8/25] Current/Best: 19.97/ 19.97 GFLOPS | Progress: (20/20) | 22.38 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.33/ 15.63 GFLOPS | Progress: (4/20) | 11.98 s
[Task 9/25] Current/Best: 22.78/ 22.78 GFLOPS | Progress: (8/20) | 13.76 s
[Task 9/25] Current/Best: 8.26/ 22.78 GFLOPS | Progress: (12/20) | 16.08 s
[Task 9/25] Current/Best: 17.99/ 22.78 GFLOPS | Progress: (16/20) | 18.74 s
[Task 9/25] Current/Best: 9.20/ 22.78 GFLOPS | Progress: (20/20) | 26.27 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (4/20) | 2.58 s
[Task 10/25] Current/Best: 15.25/ 18.28 GFLOPS | Progress: (8/20) | 4.16 s
[Task 10/25] Current/Best: 12.67/ 19.21 GFLOPS | Progress: (12/20) | 5.68 s
[Task 10/25] Current/Best: 19.10/ 20.78 GFLOPS | Progress: (16/20) | 6.78 s
[Task 10/25] Current/Best: 8.98/ 20.78 GFLOPS | Progress: (20/20
) | 8.30 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.35/ 18.16 GFLOPS | Progress: (4/20) | 3.36 s
[Task 11/25] Current/Best: 16.87/ 18.16 GFLOPS | Progress: (8/20) | 6.10 s
[Task 11/25] Current/Best: 18.27/ 18.27 GFLOPS | Progress: (12/20) | 8.16 s
[Task 11/25] Current/Best: 13.36/ 21.18 GFLOPS | Progress: (16/20) | 10.96 s
[Task 11/25] Current/Best: 19.52/ 21.54 GFLOPS | Progress: (20/20) | 12.99 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.80/ 18.00 GFLOPS | Progress: (4/20) | 5.42 s
[Task 12/25] Current/Best: 5.18/ 18.00 GFLOPS | Progress: (8/20) | 9.10 s
[Task 12/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (12/20) | 11.08 s
[Task 12/25] Current/Best: 15.23/ 18.90 GFLOPS | Progress: (16/20) | 13.84 s
[Task 12/25] Current/Best: 15.12/ 19.02 GFLOPS | Progress: (20/20) | 15.75 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 7.85/ 17.27 GFLOPS | Progress: (4/20) | 3.74 s
[Task 13/25] Current/Best: 15.97/ 20.92 GFLOPS | Progress: (8/20) | 6.16 s
[Task 13/25] Current/Best: 19.52/ 21.70 GFLOPS | Progress: (12/20) | 9.01 s
[Task 13/25] Current/Best: 12.28/ 21.70 GFLOPS | Progress: (16/20) | 12.42 s
[Task 13/25] Current/Best: 18.63/ 21.70 GFLOPS | Progress: (20/20) | 14.69 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.45/ 13.45 GFLOPS | Progress: (4/20) | 3.38 s
[Task 14/25] Current/Best: 6.09/ 13.45 GFLOPS | Progress: (8/20) | 5.55 s
[Task 14/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (12/20) | 8.13 s
[Task 14/25] Current/Best: 17.11/ 20.44 GFLOPS | Progress: (16/20) | 9.82 s Done.
-
[Task 14/25] Current/Best: 17.44/ 20.44 GFLOPS | Progress: (20/20) | 11.62 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.16/ 17.70 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.39/ 18.02 GFLOPS | Progress: (8/20) | 4.07 s
[Task 15/25] Current/Best: 10.40/ 22.37 GFLOPS | Progress: (12/20) | 6.16 s
[Task 15/25] Current/Best: 20.35/ 22.37 GFLOPS | Progress: (16/20) | 9.05 s
[Task 15/25] Current/Best: 9.71/ 22.37 GFLOPS | Progress: (20/20) | 10.03 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.25/ 20.25 GFLOPS | Progress: (4/20) | 3.02 s
[Task 16/25] Current/Best: 3.04/ 20.25 GFLOPS | Progress: (8/20) | 4.64 s
[Task 16/25] Current/Best: 19.38/ 20.25 GFLOPS | Progress: (12/20) | 5.86 s
[Task 16/25] Current/Best: 17.84/ 20.25 GFLOPS | Progress: (16/20) |
7.20 s
[Task 16/25] Current/Best: 9.98/ 22.41 GFLOPS | Progress: (20/20) | 9.25 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.49/ 18.98 GFLOPS | Progress: (4/20) | 4.73 s
[Task 17/25] Current/Best: 14.51/ 23.30 GFLOPS | Progress: (8/20) | 7.61 s
[Task 17/25] Current/Best: 16.79/ 23.30 GFLOPS | Progress: (12/20) | 9.69 s
[Task 17/25] Current/Best: 16.74/ 23.30 GFLOPS | Progress: (16/20) | 11.83 s
[Task 17/25] Current/Best: 10.05/ 23.30 GFLOPS | Progress: (20/20) | 13.95 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.03/ 17.77 GFLOPS | Progress: (4/20) | 3.73 s
[Task 18/25] Current/Best: 10.59/ 19.90 GFLOPS | Progress: (8/20) | 7.26 s
[Task 18/25] Current/Best: 19.15/ 19.90 GFLOPS | Progress: (12/20) | 9.19 s
[Task 18/25] Current/Best: 10.11/ 19.90 GFLOPS | Progress: (16/20) | 12.78 s
[Task 18/25] Current/Best: 20.67/ 20.67 GFLOPS | Progress: (20/20) | 14.29 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.06/ 20.39 GFLOPS | Progress: (4/20) | 6.09 s
[Task 19/25] Current/Best: 2.60/ 20.39 GFLOPS | Progress: (8/20) | 9.40 s
[Task 19/25] Current/Best: 17.50/ 21.18 GFLOPS | Progress: (12/20) | 12.15 s
[Task 19/25] Current/Best: 14.36/ 21.18 GFLOPS | Progress: (16/20) | 14.96 s
[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 17.80 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.79/ 14.78 GFLOPS | Progress: (4/20) | 3.34 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.49/ 17.49 GFLOPS | Progress: (4/20) | 5.90 s
[Task 1/25] Current/Best: 6.16/ 17.49 GFLOPS | Progress: (8/20) | 9.41 s
[Task 1/25] Current/Best: 11.54/ 22.79 GFLOPS | Progress: (12/20) | 11.86 s
[Task 1/25] Current/Best: 16.81/ 22.79 GFLOPS | Progress: (16/20) | 13.56 s
[Task 1/25] Current/Best: 11.58/ 23.90 GFLOPS | Progress: (20/20) | 15.30 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.04/ 13.30 GFLOPS | Progress: (4/20) | 3.82 s
[Task 2/25] Current/Best: 14.17/ 18.10 GFLOPS | Progress: (8/20) | 5.16 s
[Task 2/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (12/20) | 6.47 s
[Task 2/25] Current/Best: 12.57/ 20.98 GFLOPS | Progress: (16/20) | 7.73 s
[Task 2/25] Current/Best: 20.13/ 20.98 GFLOPS | Progress: (20/20) | 9.29 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.56 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.54/ 16.77 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.88/ 16.77 GFLOPS | Progress: (12/20) | 9.56 s
[Task 3/25] Current/Best: 7.22/ 23.74 GFLOPS | Progress: (16/20) | 11.50 s
[Task 3/25] Current/Best: 11.05/ 23.74 GFLOPS | Progress: (20/20) | 16.04 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.50/ 20.26 GFLOPS | Progress: (4/20) | 2.42 s
[Task 4/25] Current/Best: 6.78/ 20.26 GFLOPS | Progress: (8/20) | 6.75 s
[Task 4/25] Current/Best: 22.06/ 22.06 GFLOPS | Progress: (12/20) | 11.28 s
[Task 4/25] Current/Best: 17.11/ 22.06 GFLOPS | Progress: (16/20) | 13.49 s
[Task 4/25] Current/Best: 13.52/ 22.06 GFLOPS | Progress: (20/20) | 15.52 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.78/ 10.26 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.58/ 12.71 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 11.37/ 18.08 GFLOPS | Progress: (12/20) | 7.79 s
[Task 5/25] Current/Best: 11.82/ 22.55 GFLOPS | Progress: (16/20) | 9.21 s
[Task 5/25] Current/Best: 12.02/ 22.55 GFLOPS | Progress: (20/20) | 11.07 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.23/ 20.69 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 19.02/ 20.69 GFLOPS | Progress: (8/20) | 5.74 s
[Task 6/25] Current/Best: 13.33/ 20.69 GFLOPS | Progress: (12/20) | 7.67 s
[Task 6/25] Current/Best: 20.02/ 20.69 GFLOPS | Progress: (16/20) | 9.96 s
[Task 6/25] Current/Best: 3.73/ 20.69 GFLOPS | Progress: (20/20) | 12.47 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.17/ 12.89 GFLOPS | Progress: (4/20) | 3.66 s
[Task 7/25] Current/Best: 20.21/ 21.05 GFLOPS | Progress: (8/20) | 5.18 s
[Task 7/25] Current/Best: 16.04/ 21.05 GFLOPS | Progress: (12/20) | 7.08 s
[Task 7/25] Current/Best: 12.24/ 21.05 GFLOPS | Progress: (16/20) | 9.14 s
[Task 7/25] Current/Best: 6.40/ 21.75 GFLOPS | Progress: (20/20) | 11.61 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.98/ 14.27 GFLOPS | Progress: (4/20) | 2.94 s
[Task 8/25] Current/Best: 9.72/ 14.27 GFLOPS | Progress: (8/20) | 7.68 s
[Task 8/25] Current/Best: 12.77/ 14.27 GFLOPS | Progress: (12/20) | 13.76 s
[Task 8/25] Current/Best: 19.14/ 19.14 GFLOPS | Progress: (16/20) | 15.85 s
[Task 8/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (20/20) | 22.31 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.29/ 15.74 GFLOPS | Progress: (4/20) | 11.99 s
[Task 9/25] Current/Best: 23.35/ 23.35 GFLOPS | Progress: (8/20) | 13.78 s
[Task 9/25] Current/Best: 8.24/ 23.35 GFLOPS | Progress: (12/20) | 16.14 s
[Task 9/25] Current/Best: 18.01/ 23.35 GFLOPS | Progress: (16/20) | 18.80 s
[Task 9/25] Current/Best: 9.15/ 23.35 GFLOPS | Progress: (20/20) | 26.32 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (4/20) | 2.62 s
[Task 10/25] Current/Best: 15.49/ 18.17 GFLOPS | Progress: (8/20) | 4.18 s
[Task 10/25] Current/Best: 12.64/ 18.95 GFLOPS | Progress: (12/20) | 5.71 s
[Task 10/25] Current/Best: 19.06/ 20.45 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 8.91/ 20.45 GFLOPS | Progress: (20/20
) | 8.35 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.31/ 18.16 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 16.89/ 18.16 GFLOPS | Progress: (8/20) | 6.10 s
[Task 11/25] Current/Best: 18.01/ 18.16 GFLOPS | Progress: (12/20) | 8.11 s
[Task 11/25] Current/Best: 13.41/ 21.21 GFLOPS | Progress: (16/20) | 10.90 s
[Task 11/25] Current/Best: 19.48/ 21.53 GFLOPS | Progress: (20/20) | 12.90 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 18.13 GFLOPS | Progress: (4/20) | 5.30 s
[Task 12/25] Current/Best: 5.26/ 18.13 GFLOPS | Progress: (8/20) | 9.00 s
[Task 12/25] Current/Best: 18.89/ 18.89 GFLOPS | Progress: (12/20) | 11.01 s
[Task 12/25] Current/Best: 15.27/ 18.89 GFLOPS | Progress: (16/20) | 13.80 s
[Task 12/25] Current/Best: 15.08/ 18.89 GFLOPS | Progress: (20/20) | 15.72 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.85/ 17.31 GFLOPS | Progress: (4/20) | 3.70 s
[Task 13/25] Current/Best: 16.09/ 20.81 GFLOPS | Progress: (8/20) | 6.12 s
[Task 13/25] Current/Best: 19.41/ 21.22 GFLOPS | Progress: (12/20) | 8.99 s
[Task 13/25] Current/Best: 12.26/ 21.22 GFLOPS | Progress: (16/20) | 12.34 s
[Task 13/25] Current/Best: 18.13/ 21.22 GFLOPS | Progress: (20/20) | 14.61 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.66/ 13.66 GFLOPS | Progress: (4/20) | 3.40 s
[Task 14/25] Current/Best: 6.09/ 13.66 GFLOPS | Progress: (8/20) | 5.55 s
[Task 14/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (12/20) | 8.06 s
[Task 14/25] Current/Best: 16.14/ 20.65 GFLOPS | Progress: (16/20) | 9.72 s Done.
+
[Task 14/25] Current/Best: 16.94/ 20.65 GFLOPS | Progress: (20/20) | 11.54 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.14/ 17.21 GFLOPS | Progress: (4/20) | 2.76 s
[Task 15/25] Current/Best: 14.41/ 18.05 GFLOPS | Progress: (8/20) | 4.06 s
[Task 15/25] Current/Best: 10.41/ 21.64 GFLOPS | Progress: (12/20) | 6.13 s
[Task 15/25] Current/Best: 20.36/ 21.64 GFLOPS | Progress: (16/20) | 9.20 s
[Task 15/25] Current/Best: 9.72/ 21.64 GFLOPS | Progress: (20/20) | 10.22 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (4/20) | 3.09 s
[Task 16/25] Current/Best: 3.04/ 20.74 GFLOPS | Progress: (8/20) | 4.70 s
[Task 16/25] Current/Best: 19.77/ 20.74 GFLOPS | Progress: (12/20) | 5.92 s
[Task 16/25] Current/Best: 18.11/ 20.74 GFLOPS | Progress: (16/20) |
7.27 s
[Task 16/25] Current/Best: 10.07/ 22.43 GFLOPS | Progress: (20/20) | 9.31 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.72/ 18.87 GFLOPS | Progress: (4/20) | 4.76 s
[Task 17/25] Current/Best: 14.25/ 23.27 GFLOPS | Progress: (8/20) | 7.63 s
[Task 17/25] Current/Best: 16.95/ 23.27 GFLOPS | Progress: (12/20) | 9.69 s
[Task 17/25] Current/Best: 16.53/ 23.27 GFLOPS | Progress: (16/20) | 11.83 s
[Task 17/25] Current/Best: 10.04/ 23.27 GFLOPS | Progress: (20/20) | 13.97 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.22/ 18.18 GFLOPS | Progress: (4/20) | 3.74 s
[Task 18/25] Current/Best: 10.57/ 19.88 GFLOPS | Progress: (8/20) | 7.15 s
[Task 18/25] Current/Best: 18.97/ 19.88 GFLOPS | Progress: (12/20) | 9.10 s
[Task 18/25] Current/Best: 10.02/ 19.88 GFLOPS | Progress: (16/20) | 12.68 s
[Task 18/25] Current/Best: 20.42/ 20.42 GFLOPS | Progress: (20/20) | 14.21 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.13/ 20.38 GFLOPS | Progress: (4/20) | 6.12 s
[Task 19/25] Current/Best: 2.61/ 20.38 GFLOPS | Progress: (8/20) | 9.40 s
[Task 19/25] Current/Best: 18.53/ 21.40 GFLOPS | Progress: (12/20) | 12.18 s
[Task 19/25] Current/Best: 15.12/ 21.53 GFLOPS | Progress: (16/20) | 15.00 s
[Task 19/25] Current/Best: 2.70/ 23.09 GFLOPS | Progress: (20/20) | 17.84 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.10/ 15.08 GFLOPS | Progress: (4/20) | 3.43 s Done.
Done.
-
[Task 20/25] Current/Best: 10.49/ 14.78 GFLOPS | Progress: (8/20) | 6.79 s
[Task 20/25] Current/Best: 2.33/ 16.65 GFLOPS | Progress: (12/20) | 10.65 s
[Task 20/25] Current/Best: 12.58/ 16.65 GFLOPS | Progress: (16/20) | 14.48 s
[Task 20/25] Current/Best: 13.42/ 21.60 GFLOPS | Progress: (20/20) | 16.56 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.64 GFLOPS | Progress: (4/20) | 3.31 s
[Task 21/25] Current/Best: 14.48/ 17.64 GFLOPS | Progress: (8/20) | 4.88 s
[Task 21/25] Current/Best: 1.61/ 17.64 GFLOPS | Progress: (12/20) | 7.08 s
[Task 21/25] Current/Best: 16.36/ 17.64 GFLOPS | Progress: (16/20) | 10.60 s
[Task 21/25] Current/Best: 4.46/ 17.64 GFLOPS | Progress: (20/20) | 17.83 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.02 GFLOPS | Progress: (4/20
) | 2.74 s
[Task 22/25] Current/Best: 8.99/ 21.48 GFLOPS | Progress: (8/20) | 4.72 s
[Task 22/25] Current/Best: 19.75/ 21.48 GFLOPS | Progress: (12/20) | 7.03 s
[Task 22/25] Current/Best: 15.28/ 21.48 GFLOPS | Progress: (16/20) | 9.09 s
[Task 22/25] Current/Best: 15.27/ 21.48 GFLOPS | Progress: (20/20) | 10.80 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.26/ 20.28 GFLOPS | Progress: (4/20) | 3.29 s
[Task 23/25] Current/Best: 15.74/ 20.28 GFLOPS | Progress: (8/20) | 6.66 s
[Task 23/25] Current/Best: 20.75/ 21.05 GFLOPS | Progress: (12/20) | 8.49 s
[Task 23/25] Current/Best: 6.30/ 21.05 GFLOPS | Progress: (16/20) | 15.62 s
[Task 23/25] Current/Best: 7.59/ 21.05 GFLOPS | Progress: (20/20) | 19.87 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.55/ 8.55 GFLOPS | Progress: (4/20) | 11.85 s
[Task 24/25] Current/Best: 2.11/ 8.55 GFLOPS | Progress: (8/20) | 22.95 s
[Task 24/25] Current/Best: 4.16/ 8.55 GFLOPS | Progress: (12/20) | 34.51 s Done.
-
[Task 24/25] Current/Best: 7.17/ 9.01 GFLOPS | Progress: (16/20) | 39.86 s
[Task 24/25] Current/Best: 3.38/ 9.01 GFLOPS | Progress: (20/20) | 45.82 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.86 GFLOPS | Progress: (4/20) | 11.64 s
[Task 25/25] Current/Best: 5.87/ 8.01 GFLOPS | Progress: (8/20) | 22.92 s
[Task 25/25] Current/Best: 6.01/ 8.01 GFLOPS | Progress: (12/20) | 34.20 s
[Task 25/25] Current/Best: 5.77/ 8.80 GFLOPS | Progress: (16/20) | 36.02 s
[Task 25/25] Current/Best: 2.87/ 8.91 GFLOPS | Progress: (20/20) | 46.76 s
+
[Task 20/25] Current/Best: 9.71/ 15.08 GFLOPS | Progress: (8/20) | 6.73 s
[Task 20/25] Current/Best: 2.32/ 15.08 GFLOPS | Progress: (12/20) | 10.59 s
[Task 20/25] Current/Best: 12.34/ 15.08 GFLOPS | Progress: (16/20) | 14.15 s
[Task 20/25] Current/Best: 13.41/ 22.18 GFLOPS | Progress: (20/20) | 16.24 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.72 GFLOPS | Progress: (4/20) | 3.26 s
[Task 21/25] Current/Best: 14.58/ 17.72 GFLOPS | Progress: (8/20) | 4.80 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.95 s
[Task 21/25] Current/Best: 18.03/ 18.03 GFLOPS | Progress: (16/20) | 10.40 s
[Task 21/25] Current/Best: 4.47/ 18.03 GFLOPS | Progress: (20/20) | 17.47 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.91 GFLOPS | Progress: (4/20
) | 2.71 s
[Task 22/25] Current/Best: 8.76/ 21.81 GFLOPS | Progress: (8/20) | 4.70 s
[Task 22/25] Current/Best: 19.89/ 21.81 GFLOPS | Progress: (12/20) | 6.98 s
[Task 22/25] Current/Best: 15.47/ 21.81 GFLOPS | Progress: (16/20) | 9.02 s
[Task 22/25] Current/Best: 13.67/ 21.81 GFLOPS | Progress: (20/20) | 10.74 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.66/ 20.58 GFLOPS | Progress: (4/20) | 3.30 s
[Task 23/25] Current/Best: 14.10/ 20.58 GFLOPS | Progress: (8/20) | 6.67 s
[Task 23/25] Current/Best: 20.89/ 21.83 GFLOPS | Progress: (12/20) | 8.48 s
[Task 23/25] Current/Best: 6.38/ 21.83 GFLOPS | Progress: (16/20) | 15.52 s
[Task 23/25] Current/Best: 7.89/ 21.83 GFLOPS | Progress: (20/20) | 19.76 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.55/ 8.55 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 2.13/ 8.55 GFLOPS | Progress: (8/20) | 22.93 s
[Task 24/25] Current/Best: 4.22/ 8.55 GFLOPS | Progress: (12/20) | 34.50 s Done.
+
[Task 24/25] Current/Best: 6.30/ 8.67 GFLOPS | Progress: (16/20) | 39.87 s
[Task 24/25] Current/Best: 3.30/ 8.67 GFLOPS | Progress: (20/20) | 45.85 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.56/ 2.87 GFLOPS | Progress: (4/20) | 11.63 s
[Task 25/25] Current/Best: 5.67/ 7.83 GFLOPS | Progress: (8/20) | 22.91 s
[Task 25/25] Current/Best: 5.69/ 7.83 GFLOPS | Progress: (12/20) | 34.36 s
[Task 25/25] Current/Best: 5.80/ 9.44 GFLOPS | Progress: (16/20) | 36.19 s
[Task 25/25] Current/Best: 2.84/ 9.44 GFLOPS | Progress: (20/20) | 46.86 s
@@ -690,8 +690,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
- class='n02123159 tiger cat' with probability=0.356377
+ class='n02123045 tabby, tabby cat' with probability=0.621104
+ class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 419.2199781999989, 'median': 418.72353974999896, 'std': 1.3324997228142677}
- unoptimized: {'mean': 496.0577789099989, 'median': 496.2480519999872, 'std': 1.0074012982807468}
+ optimized: {'mean': 413.5104691399647, 'median': 413.1113391499639, 'std': 1.3120941368887553}
+ unoptimized: {'mean': 496.7395671700251, 'median': 496.49149335009497, 'std': 1.2848992267195383}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 17.011 seconds)
+ **Total running time of the script:** ( 10 minutes 18.827 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 0f81a1e36..01066b352 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.279e-07 secs/op
+ 1.275e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 91eed2c9d..9701ab658 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x527e780)), stage(b, placeholder(b, 0x214c4ad0)), 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, 0x200ef590)), stage(b, placeholder(b, 0x47b85f0)), 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 f11ee65ee..595342e0e 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
=================
-**13:22.942** total execution time for **tutorial** files:
+**13:19.754** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:17.011 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.827 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:07.821 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:04.819 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.373 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.220 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.477 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.008 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.850 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.349 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.709 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.704 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.522 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.660 | 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``) | 00:00.159 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.004 | 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_tvmc_command_line_driver.py` (``tvmc_command_line_driver.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 380cee1c4..f451c9f62 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -302,7 +302,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000009
- naive: 0.000007
+ naive: 0.000006
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000007
+ parallel: 0.000006
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000044
+ vector: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.75416999861045e-06 1.0
- naive 6.697300000000001e-06 0.765041117668844
- parallel 6.9378e-06 0.7925137392923872
- vector 4.4302300000000004e-05 5.060708211861559
+ numpy 9.005970005091513e-06 1.0
+ naive 5.9281e-06 0.6582411441131335
+ parallel 6.1672e-06 0.6847901998911147
+ vector 2.4559100000000003e-05 2.7269799906190615
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018383
+ Numpy running time: 0.018658
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.449179
+ none: 3.269031
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.298967
+ blocking: 0.314369
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.334051
+ vectorization: 0.342582
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.120029
+ loop permutation: 0.113940
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.111065
+ array packing: 0.108155
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111466
+ block caching: 0.110041
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.144393
+ parallelization: 0.142967
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4491794468999997 1.0
- blocking 0.2989672643 0.08667779363254097
- vectorization 0.3340514772 0.09684954997056869
- loop permutation 0.1200289599 0.03479927958166334
- array packing 0.11106480519999999 0.03220035573962993
- block caching 0.11146581120000001 0.032316617014571836
- parallelization 0.1443929044 0.041862972519384346
+ none 3.2690310261999995 1.0
+ blocking 0.3143692546 0.09616588281984903
+ vectorization 0.3425823977 0.10479631271601177
+ loop permutation 0.1139395943 0.03485424071745386
+ array packing 0.10815538170000001 0.03308484405108949
+ block caching 0.1100407087 0.03366156754648914
+ parallelization 0.14296728330000003 0.04373384105386991
@@ -1686,11 +1686,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.373 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 32e1f8465..a3332b247 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-aa97f4afb5c68e63cc19fa0279bbfa326799a6a4
+436c17f88527406fa1b014b2431609aa217dee48
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 0e2a08064..aa7cc6c9d 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.454 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.946 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 4a3cc112b..96331d6a8 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip06a98982-c9e6-43fc-89d2-da8efff4985e 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.zipdc090bfc-8f1f-4fd9-a028-634e5a031055 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 73c814888..5ac155843 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,12 +432,15 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 57.4MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 48.3MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 49.8MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 56.3MB/s]
- 90%|######### | 37.5M/41.5M [00:00<00:00, 48.4MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 40.9MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:01, 29.0MB/s]
+ 22%|##1 | 9.10M/41.5M [00:00<00:01, 26.7MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 32.8MB/s]
+ 42%|####2 | 17.5M/41.5M [00:00<00:00, 32.4MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 36.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 44.6MB/s]
+ 87%|########7 | 36.3M/41.5M [00:01<00:00, 33.1MB/s]
+ 96%|#########5| 39.8M/41.5M [00:01<00:00, 31.4MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 33.1MB/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 acc639b6e..0a37f8670 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,14 +414,10 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 16%|#6 | 7.32M/44.7M [00:00<00:00, 72.7MB/s]
- 32%|###1 | 14.3M/44.7M [00:00<00:00, 72.4MB/s]
- 47%|####7 | 21.2M/44.7M [00:00<00:00, 46.0MB/s]
- 59%|#####8 | 26.3M/44.7M [00:00<00:00, 44.3MB/s]
- 69%|######9 | 31.0M/44.7M [00:00<00:00, 44.3MB/s]
- 83%|########3 | 37.1M/44.7M [00:00<00:00, 49.6MB/s]
- 96%|#########6| 42.9M/44.7M [00:00<00:00, 52.6MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 50.4MB/s]
+ 20%|## | 9.06M/44.7M [00:00<00:00, 95.0MB/s]
+ 59%|#####8 | 26.1M/44.7M [00:00<00:00, 144MB/s]
+ 98%|#########8| 43.9M/44.7M [00:00<00:00, 163MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 154MB/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 2c2a463aa..539942bc3 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.151 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.628 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 75f815cdb..95fd9e8ae 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:06.761</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:07.104</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,43 +336,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:05.454</p></td>
+<td><p>01:06.946</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:02.151</p></td>
+<td><p>01:01.628</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:40.273</p></td>
+<td><p>00:39.336</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>00:29.006</p></td>
+<td><p>00:28.349</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:25.558</p></td>
+<td><p>00:26.040</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.938</p></td>
+<td><p>00:25.859</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.010</p></td>
+<td><p>00:22.715</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:20.218</p></td>
+<td><p>00:19.275</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>00:14.877</p></td>
+<td><p>00:14.558</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>00:02.276</p></td>
+<td><p>00:02.398</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index cea10de1f..276c9fd28 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1612 16.1079 16.8688 15.8993 0.2720
+ 16.3583 16.1126 17.2927 15.8793 0.4711
</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 6e8c95320..5e865aac0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,16 +436,46 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 7%|6 | 11.5M/170M [00:00<00:01, 121MB/s]
- 17%|#7 | 29.7M/170M [00:00<00:00, 162MB/s]
- 28%|##8 | 47.9M/170M [00:00<00:00, 175MB/s]
- 39%|###8 | 66.2M/170M [00:00<00:00, 181MB/s]
- 50%|####9 | 84.4M/170M [00:00<00:00, 185MB/s]
- 60%|###### | 102M/170M [00:00<00:00, 187MB/s]
- 71%|####### | 121M/170M [00:00<00:00, 187MB/s]
- 82%|########1 | 139M/170M [00:00<00:00, 188MB/s]
- 92%|#########2| 157M/170M [00:00<00:00, 189MB/s]
-100%|##########| 170M/170M [00:00<00:00, 183MB/s]
+ 3%|2 | 4.25M/170M [00:00<00:03, 44.5MB/s]
+ 5%|5 | 8.69M/170M [00:00<00:03, 45.5MB/s]
+ 8%|7 | 13.0M/170M [00:00<00:04, 36.3MB/s]
+ 10%|9 | 16.7M/170M [00:00<00:06, 25.1MB/s]
+ 12%|#1 | 20.2M/170M [00:00<00:05, 28.0MB/s]
+ 14%|#4 | 24.4M/170M [00:00<00:04, 31.7MB/s]
+ 16%|#6 | 27.7M/170M [00:00<00:04, 30.1MB/s]
+ 19%|#9 | 32.5M/170M [00:01<00:04, 35.4MB/s]
+ 22%|##2 | 37.7M/170M [00:01<00:03, 40.4MB/s]
+ 25%|##4 | 41.8M/170M [00:01<00:03, 39.0MB/s]
+ 27%|##7 | 46.5M/170M [00:01<00:03, 41.6MB/s]
+ 30%|##9 | 50.6M/170M [00:01<00:03, 37.9MB/s]
+ 34%|###3 | 57.0M/170M [00:01<00:02, 45.7MB/s]
+ 36%|###6 | 61.6M/170M [00:01<00:02, 39.0MB/s]
+ 39%|###8 | 66.2M/170M [00:01<00:02, 41.2MB/s]
+ 41%|####1 | 70.4M/170M [00:01<00:02, 39.6MB/s]
+ 44%|####3 | 74.3M/170M [00:02<00:02, 36.6MB/s]
+ 47%|####6 | 79.8M/170M [00:02<00:02, 41.8MB/s]
+ 50%|####9 | 84.8M/170M [00:02<00:02, 44.3MB/s]
+ 52%|#####2 | 89.1M/170M [00:02<00:02, 41.1MB/s]
+ 56%|#####5 | 94.6M/170M [00:02<00:01, 45.5MB/s]
+ 58%|#####8 | 99.1M/170M [00:02<00:01, 41.7MB/s]
+ 61%|###### | 103M/170M [00:02<00:02, 32.1MB/s]
+ 63%|######3 | 107M/170M [00:03<00:01, 34.2MB/s]
+ 65%|######5 | 111M/170M [00:03<00:01, 32.5MB/s]
+ 68%|######7 | 115M/170M [00:03<00:01, 35.8MB/s]
+ 70%|####### | 119M/170M [00:03<00:01, 35.0MB/s]
+ 73%|#######2 | 123M/170M [00:03<00:01, 36.1MB/s]
+ 75%|#######4 | 127M/170M [00:03<00:01, 35.7MB/s]
+ 77%|#######7 | 132M/170M [00:03<00:01, 39.8MB/s]
+ 80%|######## | 136M/170M [00:03<00:00, 42.7MB/s]
+ 83%|########2 | 141M/170M [00:03<00:00, 43.0MB/s]
+ 85%|########5 | 145M/170M [00:04<00:00, 34.0MB/s]
+ 87%|########7 | 148M/170M [00:04<00:00, 34.4MB/s]
+ 90%|########9 | 152M/170M [00:04<00:00, 36.0MB/s]
+ 92%|#########2| 157M/170M [00:04<00:00, 38.4MB/s]
+ 95%|#########4| 161M/170M [00:04<00:00, 38.4MB/s]
+ 97%|#########6| 164M/170M [00:04<00:00, 38.8MB/s]
+100%|#########9| 169M/170M [00:04<00:00, 40.8MB/s]
+100%|##########| 170M/170M [00:04<00:00, 37.7MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -540,7 +570,7 @@ 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 0.327 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 6.314 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 e6becd4f9..1e1c5d3b5 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,9 +480,8 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 11%|#1 | 1.52M/13.6M [00:00<00:00, 15.2MB/s]
- 29%|##8 | 3.90M/13.6M [00:00<00:00, 20.8MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 52.1MB/s]
+ 80%|#######9 | 10.8M/13.6M [00:00<00:00, 114MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 127MB/s]
</pre></div>
</div>
</div>
@@ -571,7 +570,7 @@ 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)
- 90.6549 90.6036 97.1303 90.1025 0.6928
+ 90.2902 90.2601 90.6985 90.1629 0.1012
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +609,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.859 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.504 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 24c7901c3..68cf81972 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 121.0987 120.9695 125.6456 120.1847 0.7752
+ 120.0597 119.9950 122.0563 119.1450 0.4472
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 54.936 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.582 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 92d2c9f46..d9defd541 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.834 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.219 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 c59b17c88..2b1d6076a 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,23 +441,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6184/132723 [00:00<00:02, 61830.18KB/s]
- 11%|# | 14517/132723 [00:00<00:01, 74471.65KB/s]
- 17%|#7 | 22775/132723 [00:00<00:01, 78170.38KB/s]
- 23%|##3 | 31073/132723 [00:00<00:01, 80063.79KB/s]
- 30%|##9 | 39373/132723 [00:00<00:01, 81118.43KB/s]
- 36%|###5 | 47741/132723 [00:00<00:01, 81983.33KB/s]
- 42%|####2 | 56053/132723 [00:00<00:00, 82353.45KB/s]
- 49%|####8 | 64465/132723 [00:00<00:00, 82912.60KB/s]
- 55%|#####4 | 72850/132723 [00:00<00:00, 83203.10KB/s]
- 61%|######1 | 81297/132723 [00:01<00:00, 83592.74KB/s]
- 68%|######7 | 89657/132723 [00:01<00:00, 80535.73KB/s]
- 74%|#######3 | 98033/132723 [00:01<00:00, 81489.30KB/s]
- 80%|######## | 106201/132723 [00:01<00:00, 63610.46KB/s]
- 86%|########6 | 114584/132723 [00:01<00:00, 68641.87KB/s]
- 92%|#########1| 121977/132723 [00:01<00:00, 62447.86KB/s]
- 98%|#########7| 129841/132723 [00:02<00:00, 40230.83KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 62190.36KB/s]
+ 3%|2 | 3969/132723 [00:00<00:03, 39680.39KB/s]
+ 9%|8 | 11597/132723 [00:00<00:01, 61205.74KB/s]
+ 14%|#4 | 19240/132723 [00:00<00:01, 68153.74KB/s]
+ 20%|## | 26830/132723 [00:00<00:01, 71207.53KB/s]
+ 26%|##5 | 34433/132723 [00:00<00:01, 72944.43KB/s]
+ 32%|###1 | 42094/132723 [00:00<00:01, 74188.97KB/s]
+ 37%|###7 | 49757/132723 [00:00<00:01, 74984.46KB/s]
+ 43%|####3 | 57423/132723 [00:00<00:00, 75514.02KB/s]
+ 49%|####9 | 65158/132723 [00:00<00:00, 76085.17KB/s]
+ 55%|#####4 | 72864/132723 [00:01<00:00, 76384.94KB/s]
+ 61%|###### | 80613/132723 [00:01<00:00, 76720.91KB/s]
+ 67%|######6 | 88321/132723 [00:01<00:00, 76828.21KB/s]
+ 72%|#######2 | 96012/132723 [00:01<00:00, 76851.73KB/s]
+ 78%|#######8 | 103698/132723 [00:01<00:00, 75907.90KB/s]
+ 84%|########3 | 111401/132723 [00:01<00:00, 76239.91KB/s]
+ 90%|########9 | 119031/132723 [00:01<00:00, 76255.19KB/s]
+ 95%|#########5| 126715/132723 [00:01<00:00, 76422.18KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 72400.58KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -500,7 +501,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.576 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 38.575 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 bbf2eda59..83ea8d842 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:36.474</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:45.053</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:00.327</p></td>
+<td><p>03:06.314</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:35.576</p></td>
+<td><p>02:38.575</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:54.936</p></td>
+<td><p>01:53.582</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>01:39.834</p></td>
+<td><p>01:41.219</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:10.859</p></td>
+<td><p>01:10.504</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:30.027</p></td>
+<td><p>00:30.509</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:22.745</p></td>
+<td><p>00:22.341</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.164</p></td>
+<td><p>00:22.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 5059bb059..c10ece6c6 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipd9bb0f57-139c-4ef3-95c3-ea24aa33efc3 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.zipf9aa5403-43ac-4905-8ad5-f1c910eb9971 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 71f586be0..23b75484d 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.890</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.537</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.641</p></td>
+<td><p>00:38.322</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>00:02.268</p></td>
+<td><p>00:02.270</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.973</p></td>
+<td><p>00:00.938</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 68a93da57..b9a3c2708 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6953us [6953us] (46.50%; 46.50%)
-FoldScaleAxis: 8000us [5us] (53.50%; 53.50%)
- FoldConstant: 7995us [1673us] (53.47%; 99.94%)
- InferType: 6322us [6322us] (42.28%; 79.07%)
+InferType: 6740us [6740us] (46.32%; 46.32%)
+FoldScaleAxis: 7812us [5us] (53.68%; 53.68%)
+ FoldConstant: 7806us [1629us] (53.64%; 99.93%)
+ InferType: 6177us [6177us] (42.45%; 79.13%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6481us [6481us] (44.83%; 44.83%)
-FoldScaleAxis: 7978us [5us] (55.17%; 55.17%)
- FoldConstant: 7973us [1670us] (55.14%; 99.94%)
- InferType: 6303us [6303us] (43.59%; 79.06%)
+InferType: 6184us [6184us] (42.75%; 42.75%)
+FoldScaleAxis: 8281us [5us] (57.25%; 57.25%)
+ FoldConstant: 8277us [1775us] (57.22%; 99.94%)
+ InferType: 6502us [6502us] (44.95%; 78.55%)
</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 a47da1d57..c950d2fb1 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.232151 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.182658 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 0581854bc..7c85868be 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.857927 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.292166 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 f61d23342..441a9c8f6 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019390
-Baseline: 3.444834
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019473
+Baseline: 3.407826
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.305296
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.308518
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335842
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.340642
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116988
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117791
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110721
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110714
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111310
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110970
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145615
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145490
</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 7f7b0936d..6edbb4a9f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.810</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.757</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.457</p></td>
+<td><p>00:32.537</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>00:01.251</p></td>
+<td><p>00:01.229</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>00:01.101</p></td>
+<td><p>00:00.990</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 dacb0d828..33ee8b599 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:13.013</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:15.543</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:24.257</p></td>
+<td><p>03:28.044</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:23.294</p></td>
+<td><p>01:23.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:47.555</p></td>
+<td><p>00:47.368</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:19.927</p></td>
+<td><p>00:19.462</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.025</p></td>
+<td><p>00:08.912</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.954</p></td>
+<td><p>00:08.730</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 318e05eb9..4ed4f7d8f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -491,12 +491,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [432]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -507,325 +507,1341 @@ cooperative fetching, unrolling and operator fusion.</p>
let cse_var_2: int32 = (rc.outer.outer*784)
let cse_var_1: int32 = (rc.outer.outer*144)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*2)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*2), 81)) && (floormod((threadIdx.x_1*2), 81) < 72)) && (1 <= floormod((threadIdx.x_1*2), 9))) && (floormod((threadIdx.x_1*2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*2), 81)*49)) + (floordiv(floormod((threadIdx.x_1*2), 81), 9)*7)) + floormod((threadIdx.x_1*2), 9)) - 8 [...]
- pad_temp.shared_1[((threadIdx.x_1*2) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 1), 81)) && (floormod(((threadIdx.x_1*2) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 1), 9))) && (floormod(((threadIdx.x_1*2) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- pad_temp.shared_1[((threadIdx.x_1*2) + 448)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 43), 81)) && (floormod(((threadIdx.x_1*2) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 7), 9))) && (floormod(((threadIdx.x_1*2) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 448), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 43), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*2) + 449)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 44), 81)) && (floormod(((threadIdx.x_1*2) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 8), 9))) && (floormod(((threadIdx.x_1*2) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 449), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 44), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- if @tir.likely((threadIdx.x_1 < 200), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 896)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 5), 81)) && (floormod(((threadIdx.x_1*2) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 5), 9))) && (floormod(((threadIdx.x_1*2) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 896), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 200), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*2) + 897)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*2) + 6), 81)) && (floormod(((threadIdx.x_1*2) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*2) + 6), 9))) && (floormod(((threadIdx.x_1*2) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*2) + 897), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*2) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*2) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 96), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 5), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 4), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 48), 144), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 8), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((threadIdx.x_2 < 128), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [432], [], 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[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod( [...]
+ 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 5), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 10), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 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 + 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 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 + 192)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 1), 9)) && (floormod((threadIdx.x_1 + 3), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 1), 9)*7)) + floormod(blockIdx.x, 7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 8), 27)) && (floormod((threadIdx.x_1 + 8), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 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 + 256)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 13), 27)) && (floormod((threadIdx.x_1 + 13), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 256), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 13), 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 + 288)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 6), 9)) && (floormod((threadIdx.x_1 + 18), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 288), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 6), 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 + 320)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 23), 27)) && (floormod((threadIdx.x_1 + 23), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 320), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 23), 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 + 352)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 1), 27)) && (floormod((threadIdx.x_1 + 1), 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[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 352), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 1), 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 + 384)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 2), 9)) && (floormod((threadIdx.x_1 + 6), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 384), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 2), 9)*7)) + floormod(blockIdx.x, 7)) + floormod [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ if @tir.likely((threadIdx.x_1 < 16), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 416)] = @tir.if_then_else((((threadIdx.x_1 < 13) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 416), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 11), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
}
+ 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[(((floordiv(blockIdx.x, 7)*147456) + 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[((((floordiv(blockIdx.x, 7)*147456) + 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 64), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 96)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 128), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 192), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 224), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 320), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 384), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 480), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 512), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 608)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 608), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 704), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 768), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 800), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 832), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 896), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 928), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 960), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 992), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1024), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1056), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1120), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 1184)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1184), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1216), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1248), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1344), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1376), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1472), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1504), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1536), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1568), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1600), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1632), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1664), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1696), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 1760)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1760), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1792), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1824), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1856), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1888), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1920), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 1984), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2048), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2112), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2144), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2176), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2208), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2240), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2272), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 2336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2336), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2368), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2400), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2432), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2464), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2496), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2528), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2560), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2656), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2720), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2784), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2816), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2848), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 2912)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2912), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2944), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 2976), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3008), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3040), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3072), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3104), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3136), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3200), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3232), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3264), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3328), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3360), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 3488)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3488), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3520), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3552), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3584), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3648), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3680), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3712), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3776), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3808), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3840), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3872), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3904), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3936), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 3968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4000), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + 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 + 4064)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4096), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4128), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4160), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4192), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4224), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4256), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4352), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4384), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4416), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 32)*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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4448), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4480), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4512), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4544), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 144), 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[(((((floordiv(blockIdx.x, 7)*147456) + (floordiv((threadIdx.x_2 + 4576), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 144), 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[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[216]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[219]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[219]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[237]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[237]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[240]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[243]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[246]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[246]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[264]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[264]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[267]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[217]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[220]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[220]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[238]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[238]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[241]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[244]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[247]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[247]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[265]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[265]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[268]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[218]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[221]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[221]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[239]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[239]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[242]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[245]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[248]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[248]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[266]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[266]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[269]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[270]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[273]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[273]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[291]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[291]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[294]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[297]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[300]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[300]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[318]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[318]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[321]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[271]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[274]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[274]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[292]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[292]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[295]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[298]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[301]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[301]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[319]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[319]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[322]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[272]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[275]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[275]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[293]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[293]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[296]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[299]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[302]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[302]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[320]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[320]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[323]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[324]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[327]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[327]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[345]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[345]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[348]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[351]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[354]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[354]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[372]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[372]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[375]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[325]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[328]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[328]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[346]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[346]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[349]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[352]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[355]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[355]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[373]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[373]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[376]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[326]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[329]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[329]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[347]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[347]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[350]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[353]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[356]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[356]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[374]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[374]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[377]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[378]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[381]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[381]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[399]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[399]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[402]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[405]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[408]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[408]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[426]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[426]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[429]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[379]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[382]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[382]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[400]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[400]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[403]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[406]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[409]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[409]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[427]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[427]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[430]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[380]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[383]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[383]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[401]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[401]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[404]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[407]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[410]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[410]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[428]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[428]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[431]*kernel.shared_1[((threadIdx.x*144) + 143)]))
}
}
- for (i3.inner: int32, 0, 7) {
- compute[(((blockIdx.x*1568) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias[((blockIdx.x*32) + floordiv(threadIdx.x, 7))]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
}
}
</pre></div>
@@ -861,7 +1877,7 @@ 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: 0.198 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.215 ms
</pre></div>
</div>
</div>
@@ -896,18 +1912,18 @@ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
-conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+conv2d_nchw_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=7)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+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=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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)
@@ -916,9 +1932,9 @@ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
-compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_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=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
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)
@@ -939,14 +1955,14 @@ 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=224)
+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)
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=2)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+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)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -964,9 +1980,9 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[7];
- __shared__ float pad_temp_shared[1296];
+ __shared__ float pad_temp_shared[432];
__shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -977,298 +1993,1183 @@ extern "C" __global__ void __launch_bounds__(224) default_function_ker
conv2d_nchw[6] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 2)] = (((((9 <= ((((int)threadIdx.x) * 2) % 81)) && (((((int)threadIdx.x) * 2) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 2) % 9))) && (((((int)threadIdx.x) * 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 2) / 81) * 49)) + ((((((int)threadIdx.x) * 2) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 1)] = (((((9 <= (((((int)threadIdx.x) * 2) + 1) % 81)) && ((((((int)threadIdx.x) * 2) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 1) % 9))) && ((((((int)threadIdx.x) * 2) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 448)] = (((((9 <= (((((int)threadIdx.x) * 2) + 43) % 81)) && ((((((int)threadIdx.x) * 2) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 7) % 9))) && ((((((int)threadIdx.x) * 2) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 448) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 43) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 2) + 449)] = (((((9 <= (((((int)threadIdx.x) * 2) + 44) % 81)) && ((((((int)threadIdx.x) * 2) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 8) % 9))) && ((((((int)threadIdx.x) * 2) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 449) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 44) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 8) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 200) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 896)] = (((((9 <= (((((int)threadIdx.x) * 2) + 5) % 81)) && ((((((int)threadIdx.x) * 2) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 5) % 9))) && ((((((int)threadIdx.x) * 2) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 896) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 200) {
- pad_temp_shared[((((int)threadIdx.x) * 2) + 897)] = (((((9 <= (((((int)threadIdx.x) * 2) + 6) % 81)) && ((((((int)threadIdx.x) * 2) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 2) + 6) % 9))) && ((((((int)threadIdx.x) * 2) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 2) + 897) / 81) * 49)) + (((((((int)threadIdx.x) * 2) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 2) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 96) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 4) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 48) % 144) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 80) % 144) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 128) {
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ 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 * 784) + ((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((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 * 784) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= (((((int)threadIdx.x) / 3) + 1) % 9)) && (((((int)threadIdx.x) + 3) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 1) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((3 <= ((((int)threadIdx.x) + 8) % 27)) && (((((int)threadIdx.x) + 8) % 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 * 784) + (((((int)threadIdx.x) + 224) / 27) * 49)) + ((((((int)threadIdx.x) + 8) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 256)] = (((((3 <= ((((int)threadIdx.x) + 13) % 27)) && (((((int)threadIdx.x) + 13) % 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 * 784) + (((((int)threadIdx.x) + 256) / 27) * 49)) + ((((((int)threadIdx.x) + 13) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 288)] = (((((1 <= (((((int)threadIdx.x) / 3) + 6) % 9)) && (((((int)threadIdx.x) + 18) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 288) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 6) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 320)] = (((((3 <= ((((int)threadIdx.x) + 23) % 27)) && (((((int)threadIdx.x) + 23) % 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 * 784) + (((((int)threadIdx.x) + 320) / 27) * 49)) + ((((((int)threadIdx.x) + 23) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + [...]
+ pad_temp_shared[(((int)threadIdx.x) + 352)] = (((((3 <= ((((int)threadIdx.x) + 1) % 27)) && (((((int)threadIdx.x) + 1) % 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 * 784) + (((((int)threadIdx.x) + 352) / 27) * 49)) + ((((((int)threadIdx.x) + 1) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 384)] = (((((1 <= (((((int)threadIdx.x) / 3) + 2) % 9)) && (((((int)threadIdx.x) + 6) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 384) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : [...]
+ if (((int)threadIdx.x) < 16) {
+ pad_temp_shared[(((int)threadIdx.x) + 416)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 416) / 27) * 49)) + (((((int)threadIdx.x) + 11) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1184) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1216) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1312) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1376) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1408) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1504) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1600) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1632) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1664) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1696) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1760) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1888) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1984) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2048) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2208) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2272) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2336) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2368) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2432) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2528) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2560) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2656) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2816) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2848) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2944) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 2976) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3008) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3040) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3072) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3104) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3200) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3264) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3328) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3392) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3424) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3488) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3520) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3552) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3648) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3680) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3712) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3776) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3872) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3936) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 3968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4000) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4096) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4160) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4192) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4288) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4352) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4384) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96)];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4544) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 4576) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 112) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- }
- }
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 1568) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[216] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[219] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[219] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[237] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[237] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[240] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[243] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[246] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[246] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[264] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[264] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[267] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[217] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[220] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[220] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[238] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[238] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[241] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[244] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[247] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[247] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[265] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[265] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[268] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[218] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[221] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[221] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[239] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[239] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[242] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[245] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[248] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[248] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[266] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[266] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[269] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[270] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[273] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[273] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[291] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[291] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[294] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[297] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[300] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[300] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[318] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[318] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[321] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[271] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[274] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[274] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[292] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[292] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[295] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[298] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[301] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[301] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[319] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[319] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[322] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[272] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[275] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[275] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[293] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[293] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[296] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[299] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[302] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[302] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[320] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[320] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[323] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[324] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[327] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[327] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[345] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[345] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[348] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[351] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[354] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[354] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[372] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[372] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[375] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[325] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[328] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[328] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[346] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[346] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[349] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[352] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[355] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[355] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[373] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[373] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[376] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[326] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[329] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[329] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[347] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[347] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[350] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[353] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[356] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[356] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[374] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[374] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[377] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[378] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[381] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[381] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[399] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[399] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[402] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[405] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[408] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[408] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[426] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[426] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[429] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[379] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[382] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[382] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[400] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[400] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[403] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[406] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[409] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[409] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[427] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[427] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[430] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[380] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[383] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[383] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[401] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[401] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[404] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[407] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[410] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[410] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[428] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[428] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[431] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1304,7 +3205,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 24.257 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.044 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 746b98bcb..36f502f2b 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8389 9.8324 9.8854 9.7990 0.0356
+ 9.9080 9.9079 9.9352 9.8808 0.0222
</pre></div>
</div>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
index 1023615ac..657e9ecd1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.8519 755.3273 755.6256 753.6029 0.8916
+ 746.5228 745.6988 748.5021 745.3677 1.4060
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.294 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.027 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 35188a9c0..7113dea77 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,217 +625,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_1: int32 = ((i.outer.inner*128) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_67: int32 = (i.outer.inner*1024)
- let cse_var_66: int32 = (elem_idx*16)
- let cse_var_65: int32 = (cse_var_1 + 99)
- let cse_var_64: int32 = (cse_var_1 + 98)
- let cse_var_63: int32 = (cse_var_1 + 97)
- let cse_var_62: int32 = (cse_var_1 + 96)
- let cse_var_61: int32 = (cse_var_1 + 9)
- let cse_var_60: int32 = (cse_var_1 + 8)
- let cse_var_59: int32 = (cse_var_1 + 79)
- let cse_var_58: int32 = (cse_var_1 + 78)
- let cse_var_57: int32 = (cse_var_1 + 77)
- let cse_var_56: int32 = (cse_var_1 + 76)
- let cse_var_55: int32 = (cse_var_1 + 75)
- let cse_var_54: int32 = (cse_var_1 + 74)
- let cse_var_53: int32 = (cse_var_1 + 73)
- let cse_var_52: int32 = (cse_var_1 + 72)
- let cse_var_51: int32 = (cse_var_1 + 71)
- let cse_var_50: int32 = (cse_var_1 + 70)
- let cse_var_49: int32 = (cse_var_1 + 7)
- let cse_var_48: int32 = (cse_var_1 + 69)
- let cse_var_47: int32 = (cse_var_1 + 68)
- let cse_var_46: int32 = (cse_var_1 + 67)
- let cse_var_45: int32 = (cse_var_1 + 66)
- let cse_var_44: int32 = (cse_var_1 + 65)
- let cse_var_43: int32 = (cse_var_1 + 64)
- let cse_var_42: int32 = (cse_var_1 + 6)
- let cse_var_41: int32 = (cse_var_1 + 5)
- let cse_var_40: int32 = (cse_var_1 + 47)
- let cse_var_39: int32 = (cse_var_1 + 46)
- let cse_var_38: int32 = (cse_var_1 + 45)
- let cse_var_37: int32 = (cse_var_1 + 44)
- let cse_var_36: int32 = (cse_var_1 + 43)
- let cse_var_35: int32 = (cse_var_1 + 42)
- let cse_var_34: int32 = (cse_var_1 + 41)
- let cse_var_33: int32 = (cse_var_1 + 40)
- let cse_var_32: int32 = (cse_var_1 + 4)
- let cse_var_31: int32 = (cse_var_1 + 39)
- let cse_var_30: int32 = (cse_var_1 + 38)
- let cse_var_29: int32 = (cse_var_1 + 37)
- let cse_var_28: int32 = (cse_var_1 + 36)
- let cse_var_27: int32 = (cse_var_1 + 35)
- let cse_var_26: int32 = (cse_var_1 + 34)
- let cse_var_25: int32 = (cse_var_1 + 33)
- let cse_var_24: int32 = (cse_var_1 + 32)
- let cse_var_23: int32 = (cse_var_1 + 3)
- let cse_var_22: int32 = (cse_var_1 + 2)
- let cse_var_21: int32 = (cse_var_1 + 15)
- let cse_var_20: int32 = (cse_var_1 + 14)
- let cse_var_19: int32 = (cse_var_1 + 13)
- let cse_var_18: int32 = (cse_var_1 + 12)
- let cse_var_17: int32 = (cse_var_1 + 111)
- let cse_var_16: int32 = (cse_var_1 + 110)
- let cse_var_15: int32 = (cse_var_1 + 11)
- let cse_var_14: int32 = (cse_var_1 + 109)
- let cse_var_13: int32 = (cse_var_1 + 108)
- let cse_var_12: int32 = (cse_var_1 + 107)
- let cse_var_11: int32 = (cse_var_1 + 106)
- let cse_var_10: int32 = (cse_var_1 + 105)
- let cse_var_9: int32 = (cse_var_1 + 104)
- let cse_var_8: int32 = (cse_var_1 + 103)
- let cse_var_7: int32 = (cse_var_1 + 102)
- let cse_var_6: int32 = (cse_var_1 + 101)
- let cse_var_5: int32 = (cse_var_1 + 100)
- let cse_var_4: int32 = (cse_var_1 + 10)
- let cse_var_3: int32 = (cse_var_1 + 1)
- {
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[(cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_37] = (compute_5[cse_var_37] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_66)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 1)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 2)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 3)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 4)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 5)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 6)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 7)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 8)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 9)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 10)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 11)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 12)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 13)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 14)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_66) + 15)]*max(placeholder[((cse_var_67 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
+ for (i.inner.init: int32, 0, 2) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [2048], [])[((((i.outer.inner*64) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 2) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*64) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i.outer.inner*512)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_68: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_68, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_68, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -873,7 +686,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.019 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.117 ms
</pre></div>
</div>
<div class="admonition note">
diff --git a/docs/how_to/tune_with_autotvm/sg_execution_times.html b/docs/how_to/tune_with_autotvm/sg_execution_times.html
index e238f229a..380781eb3 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.108</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.734</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.073</p></td>
+<td><p>00:45.697</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.019</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index a5d145d82..e1c218a9f 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 80.76/80.76 result: MeasureResult(costs=(0.0028664421142857144,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8323888778686523, timestamp=1660816877.334716) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/80.76 result: Traceback (most recent call last):
+No: 9 GFLOPS: 220.36/220.36 result: MeasureResult(costs=(0.0010505666896551723,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9906036853790283, timestamp=1660816717.9250998) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/220.36 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.97/260.97 result: MeasureResult(costs=(0.0008870664917127072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.728985071182251, timestamp=1660816878.2587764) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 11 GFLOPS: 261.47/261.47 result: MeasureResult(costs=(0.0008853753093922652,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7667784690856934, timestamp=1660816718.856316) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.31/260.97 result: MeasureResult(costs=(0.0436249185,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8379912376403809, timestamp=1660816882.8576086) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.34/260.97 result: MeasureResult(costs=(0.06930364874999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.6043665409088135, timestamp=1660816884.0969527) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.36/261.47 result: MeasureResult(costs=(0.043183570500000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8371973037719727, timestamp=1660816723.4216356) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.36/261.47 result: MeasureResult(costs=(0.068981317,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.5557684898376465, timestamp=1660816724.6612272) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.13/260.97 result: MeasureResult(costs=(0.008230546714285714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2766973972320557, timestamp=1660816895.1346583) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 18 GFLOPS: 27.59/261.47 result: MeasureResult(costs=(0.008389330642857143,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2751076221466064, timestamp=1660816735.6851811) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.97 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/261.47 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001270
+Time cost of this operator: 0.001217
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 44442bfa3..f83df0dc5 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.3 98.725 (1, 2, 10, 10, 3) 2 1 [309.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.031 0.967 (1, 6, 10, 10) 1 1 [3.031]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.307 (1, 1, 10, 10, 3) 1 1 [0.962]
-Total_time - 313.293 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.733 (1, 2, 10, 10, 3) 2 1 [310.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.017 0.959 (1, 6, 10, 10) 1 1 [3.017]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.971 0.308 (1, 1, 10, 10, 3) 1 1 [0.971]
+Total_time - 314.688 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 119.8 97.748 (1, 6, 10, 10, 1) 2 1 [119.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.807 1.474 (1, 6, 10, 10) 1 1 [1.807]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.953 0.778 (1, 1, 10, 10, 3) 1 1 [0.953]
-Total_time - 122.56 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 130.0 97.897 (1, 6, 10, 10, 1) 2 1 [130.0]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.808 1.362 (1, 6, 10, 10) 1 1 [1.808]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.741 (1, 1, 10, 10, 3) 1 1 [0.984]
+Total_time - 132.793 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 4b38f7094..7902f430e 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpnxg7j5g1/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpxmt6h_yv/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpnxg7j5g1/images/target contains 8144 images
-/tmp/tmpnxg7j5g1/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpxmt6h_yv/images/target contains 8144 images
+/tmp/tmpxmt6h_yv/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2389 - accuracy: 0.9192 - val_loss: 0.1476 - val_accuracy: 0.9585
+328/328 - 55s - loss: 0.2318 - accuracy: 0.9206 - val_loss: 0.1407 - val_accuracy: 0.9573
Epoch 2/3
-328/328 - 53s - loss: 0.1039 - accuracy: 0.9615 - val_loss: 0.1319 - val_accuracy: 0.9577
+328/328 - 52s - loss: 0.1050 - accuracy: 0.9612 - val_loss: 0.1237 - val_accuracy: 0.9645
Epoch 3/3
-328/328 - 52s - loss: 0.0653 - accuracy: 0.9752 - val_loss: 0.1104 - val_accuracy: 0.9622
+328/328 - 52s - loss: 0.0658 - accuracy: 0.9755 - val_loss: 0.1786 - val_accuracy: 0.9532
-<keras.callbacks.History object at 0x7f488894af50>
+<keras.callbacks.History object at 0x7f5dbc73e610>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 39.005 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 9.377 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index c7d31cc33..cdd3fa899 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:32.704</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:02.215</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:39.005</p></td>
+<td><p>06:09.377</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.652</p></td>
+<td><p>00:42.026</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:07.641</p></td>
+<td><p>00:07.518</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.404</p></td>
+<td><p>00:03.293</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index f9771fc00..4dd42c06a 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:41.121</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:38.456</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.043</p></td>
+<td><p>00:30.818</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:08.629</p></td>
+<td><p>00:06.312</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.442</p></td>
+<td><p>00:01.318</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 2bb8985a7..baa16a65c 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f4888fa8200>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f5d2b47e0e0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index e186c1050..5d96c9593 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.122</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:03.928</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,23 +336,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.911</p></td>
+<td><p>00:01.818</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.976</p></td>
+<td><p>00:00.919</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.530</p></td>
+<td><p>00:00.513</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.520</p></td>
+<td><p>00:00.495</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.102</p></td>
+<td><p>00:00.100</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -360,7 +360,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 1b64887cb..934d91403 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpmz9u91pi/input0.cc'\nsource_filename = \"/tmp/tmpmz9u91pi/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpv70ud6xb/input0.cc'\nsource_filename = \"/tmp/tmpv70ud6xb/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 788dc94bb..95398874e 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1886,7 +1886,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 10644aa89..c4c9851d9 100644
--- a/docs/reference/api/typedoc/classes/bytestreamreader.html
+++ b/docs/reference/api/typedoc/classes/bytestreamreader.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 9dba2a81f..deec4a8a9 100644
--- a/docs/reference/api/typedoc/classes/cachedcallstack.html
+++ b/docs/reference/api/typedoc/classes/cachedcallstack.html
@@ -144,7 +144,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aa97f4afb/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/436c17f88/web/src/memory.ts#L223">memory.ts:223</a></li>
... 2873 lines suppressed ...