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 2022/07/13 00:25:58 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@1d5d357d69ab8a0ceae047532ab778359676cda7)
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 0af87de49 deploying docs (apache/tvm@1d5d357d69ab8a0ceae047532ab778359676cda7)
0af87de49 is described below
commit 0af87de4982dae94853c6845d8d69a86f2b7939a
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jul 13 00:25:52 2022 +0000
deploying docs (apache/tvm@1d5d357d69ab8a0ceae047532ab778359676cda7)
---
.../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 | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2225 ++++++++++++--------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 35 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../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 | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../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 | 14 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 42 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 13 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 34 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 19 +-
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 | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2225 ++++++++++++--------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 35 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
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 | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
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 | 6 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +-
docs/tutorial/tensor_expr_get_started.html | 42 +-
121 files changed, 3490 insertions(+), 2659 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 63172d3d3..5a0d8dea2 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 0.160 seconds)
+ **Total running time of the script:** ( 1 minutes 1.459 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 97f143081..33bb21bc3 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.zipdedc4325-5145-42e6-b6e6-cc9e05eb956a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip49e85b8a-b60f-4ccc-8dff-5950c66cf008 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 5cefd0787..00f978735 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, 78.9MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 56.9MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 55.8MB/s]
71%|#######1 | 29.5M/41.5M [00:00<00:00, 55.0MB/s]
84%|########4 | 34.9M/41.5M [00:00<00:00, 53.3MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 53.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 56.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 42.8MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 45.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 40.8MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 46.9MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 51.1MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 47.1MB/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 d4658d6a4..c62b068db 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]
43%|####3 | 19.3M/44.7M [00:00<00:00, 202MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 236MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
9%|9 | 4.10M/44.7M [00:00<00:00, 43.0MB/s]
18%|#8 | 8.20M/44.7M [00:00<00:00, 41.7MB/s]
63%|######3 | 28.2M/44.7M [00:00<00:00, 116MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 120MB/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 7a0271e5d..c7a7f9885 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.251 seconds)
+ **Total running time of the script:** ( 1 minutes 4.133 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 14e7b1dfa..8cdc0f0b8 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
=================
-**04:54.746** total execution time for **how_to_compile_models** files:
+**05:18.936** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.251 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.133 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:00.160 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:01.459 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.171 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:39.327 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:26.210 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:32.825 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.877 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:25.874 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.301 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.555 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.852 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.249 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.888 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.021 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.660 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.118 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.376 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.375 | 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 478b2ce46..f4e37c6de 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)
- 16.0698 15.7823 18.1002 15.7034 0.6941
+ 17.8958 16.2035 28.7124 16.1167 3.8020
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 7c868fd04..087b1c35c 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]
11%|#1 | 19.3M/170M [00:00<00:00, 202MB/s]
26%|##6 | 44.6M/170M [00:00<00:00, 240MB/s]
41%|####1 | 69.9M/170M [00:00<00:00, 251MB/s]
56%|#####6 | 95.4M/170M [00:00<00:00, 257MB/s]
71%|#######1 | 121M/170M [00:00<00:00, 262MB/s]
86%|########6 | 147M/170M [00:00<00:00, 265MB/s]
100%|##########| 170M/170M [00:00<00:00, 257MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 3.34M/170M [00:00<00:04, 35.1MB/s]
4%|3 | 6.77M/170M [00:00<00:04, 35.5MB/s]
13%|#2 | 21.8M/170M [00:00<00:01, 91.4MB/s]
28%|##7 | 47.5M/170M [00:00<00:00, 161MB/s]
43%|####2 | 72.8M/170M [00:00<00:00, 199MB/s]
54%|#####4 | 91.8M/170M [00:00<00:00, 184MB/s]
65%|######5 | 111M/170M [00:00<00:00, 186MB/s]
78%|#######7 | 132M/170M [00:00<00:00, 197MB/s]
91%|#########1| 155M/170M [00:00<00:00, 208MB/s]
100%|##########| 170M/170M [00:01<00:00, 177MB/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:** ( 2 minutes 52.075 seconds)
+ **Total running time of the script:** ( 3 minutes 0.309 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 3620459e1..35bb968bc 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 171MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
23%|##2 | 3.12M/13.6M [00:00<00:00, 32.6MB/s]
55%|#####5 | 7.48M/13.6M [00:00<00:00, 40.3MB/s]
88%|########7 | 11.9M/13.6M [00:00<00:00, 42.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 41.4MB/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)
- 90.2850 90.2593 91.3379 90.1044 0.1477
+ 90.4858 90.3755 94.1574 90.2464 0.4623
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.949 seconds)
+ **Total running time of the script:** ( 1 minutes 8.747 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 29e916687..3e5548b61 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)
- 118.6430 118.5980 121.1373 117.7792 0.3988
+ 122.1050 122.0081 124.2679 121.2033 0.4942
@@ -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 57.107 seconds)
+ **Total running time of the script:** ( 2 minutes 3.898 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 afa99241d..5ffdb2894 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 20.168 seconds)
+ **Total running time of the script:** ( 1 minutes 24.520 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 0f0d43c50..8005ba399 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5744/132723 [00:00<00:02, 57433.76KB/s]
10%|# | 13424/132723 [00:00<00:01, 68822.10KB/s]
15%|#5 | 20307/132723 [00:00<00:01, 58900.41KB/s]
21%|##1 | 28339/132723 [00:00<00:01, 66572.00KB/s]
26%|##6 | 35163/132723 [00:00<00:02, 36370.13KB/s]
33%|###2 | 43222/132723 [00:00<00:01, 45549.53KB/s]
37%|###7 | 49306/132723 [00:01<00:03, 26536.74KB/s]
43%|####3 | 57225/132723 [00:01<00:02, 34446.29KB/s]
49%|####9 | 65453/132723 [00:01<00:01, 42897.01KB/s]
54%|#####4 | 71875/132723 [00:01<00:02, 29620.61KB/s]
60%|###### | 79969/132723 [00:02<00:01, 37474.29KB/s]
65%|######4 | 85876/132723 [00:02<00:01, 35662.82KB/s]
71%|####### | 93992/132723 [00:02<00:00, 43899.02KB/s]
77%|#######6 | 102013/132723 [00:02<00:00, 51358.64KB/s]
83%|########3 | 110165/132723 [00:02<00:00, 58202.16KB/s]
88%|########8
| 117233/132723 [00:02<00:00, 60097.65KB/s]
94%|#########4| 125219/132723 [00:02<00:00, 65145.33KB/s]
100%|##########| 132723/132723 [00:02<00:00, 46704.19KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5325/132723 [00:00<00:02, 53241.17KB/s]
10%|# | 13279/132723 [00:00<00:01, 68705.52KB/s]
16%|#6 | 21447/132723 [00:00<00:01, 74626.37KB/s]
22%|##2 | 29562/132723 [00:00<00:01, 77199.94KB/s]
28%|##8 | 37678/132723 [00:00<00:01, 78625.54KB/s]
34%|###4 | 45677/132723 [00:00<00:01, 79087.41KB/s]
40%|#### | 53586/132723 [00:00<00:01, 78944.61KB/s]
46%|####6 | 61481/132723 [00:00<00:00, 78437.73KB/s]
52%|#####2 | 69326/132723 [00:00<00:00, 78052.42KB/s]
58%|#####8 | 77168/132723 [00:01<00:00, 78162.55KB/s]
64%|######4 | 84985/132723 [00:01<00:00, 77926.86KB/s]
70%|######9 | 92849/132723 [00:01<00:00, 78134.62KB/s]
76%|#######5 | 100663/132723 [00:01<00:00, 78083.29KB/s]
82%|########1 | 108498/132723 [00:01<00:00, 78160.92KB/s]
88%|########7 | 116361/132723 [00:01<00:00, 78298.53KB/s]
94%|########
#3| 124192/132723 [00:01<00:00, 78256.36KB/s]
100%|#########9| 132229/132723 [00:01<00:00, 78887.98KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77449.18KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 19.183 seconds)
+ **Total running time of the script:** ( 2 minutes 24.028 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 7778629f7..8d8f72290 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
@@ -5,22 +5,22 @@
Computation times
=================
-**10:24.333** total execution time for **how_to_deploy_models** files:
+**10:52.850** 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``) | 02:52.075 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:00.309 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:19.183 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:24.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:57.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:03.898 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:20.168 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:24.520 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.949 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.747 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.249 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.249 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.092 | 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 b78ab6172..ec4928a32 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.zip80654098-a492-46da-a9fe-3ca654536d48 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip8ec81053-9169-4f5a-87b9-d1cfb4ce2a2b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -590,7 +590,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
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 cfcbb8146..8f7007eac 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
=================
-**00:39.436** total execution time for **how_to_extend_tvm** files:
+**00:40.939** 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``) | 00:36.373 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.691 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.154 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.302 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.901 | 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 |
+-------------------------------------------------------------------------------------------------+-----------+--------+
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 a9ca08da7..7c0c8060e 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: 6497us [6497us] (45.62%; 45.62%)
- FoldScaleAxis: 7744us [6us] (54.38%; 54.38%)
- FoldConstant: 7739us [1563us] (54.34%; 99.93%)
- InferType: 6176us [6176us] (43.36%; 79.80%)
+ InferType: 6718us [6718us] (45.51%; 45.51%)
+ FoldScaleAxis: 8045us [6us] (54.49%; 54.49%)
+ FoldConstant: 8039us [1637us] (54.45%; 99.92%)
+ InferType: 6401us [6401us] (43.36%; 79.63%)
@@ -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: 6152us [6152us] (44.62%; 44.62%)
- FoldScaleAxis: 7635us [5us] (55.38%; 55.38%)
- FoldConstant: 7630us [1594us] (55.35%; 99.94%)
- InferType: 6037us [6037us] (43.79%; 79.11%)
+ InferType: 6297us [6297us] (44.12%; 44.12%)
+ FoldScaleAxis: 7977us [5us] (55.88%; 55.88%)
+ FoldConstant: 7972us [1652us] (55.85%; 99.93%)
+ InferType: 6320us [6320us] (44.27%; 79.28%)
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 86372c13f..84efdaa6b 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: 48.468963 ms
+ Convolution: 33.139916 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 3d52d074e..8b1c520dc 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: 6.852600 ms
+ conv2d with tensor core: 13.368312 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 97cc75cc4..8b4110119 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: 0.018232
- Baseline: 3.196743
+ Numpy running time: 0.019177
+ Baseline: 3.343142
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.297766
+ Opt1: 0.318190
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335953
+ Opt2: 0.349233
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117141
+ Opt3: 0.121343
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110547
+ Opt4: 0.111546
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110636
+ Opt5: 0.112412
@@ -810,7 +810,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144786
+ Opt6: 0.146764
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 87afa1009..d753187d6 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
=================
-**00:33.732** total execution time for **how_to_optimize_operators** files:
+**00:34.955** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.442 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.584 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.263 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.364 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.008 | 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 62d6110af..f8b5ecc9e 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
=================
-**05:12.565** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:17.345** 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``) | 02:35.326 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:38.212 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.799 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:20.692 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:42.911 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.640 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.715 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.534 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.525 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.693 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.288 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.574 | 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 8a9e45ee7..a11e78eaf 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -240,483 +240,717 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 32) {
+ 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" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*4), 81)) && (floormod((threadIdx.x_1*4), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 81)*49)) + (floordiv(floormod((threadIdx.x_1*4), 81), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 1), 81)) && (floormod(((threadIdx.x_1*4) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 2), 81)) && (floormod(((threadIdx.x_1*4) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 3), 81)) && (floormod(((threadIdx.x_1*4) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 224)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 62), 81)) && (floormod(((threadIdx.x_1*4) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 224), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 62), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 225)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 9) + 7), 9)) && (floormod(((threadIdx.x_1*4) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 225), 81)*49)) + (floormod((floordiv((threadIdx.x_1*4), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 226)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 64), 81)) && (floormod(((threadIdx.x_1*4) + 64), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 226), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 64), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 227)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 65), 81)) && (floormod(((threadIdx.x_1*4) + 65), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 227), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 65), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 448)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 43), 81)) && (floormod(((threadIdx.x_1*4) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 448), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 43), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 449)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 44), 81)) && (floormod(((threadIdx.x_1*4) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 449), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 44), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 450)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 9) + 5), 9)) && (floormod(((threadIdx.x_1*4) + 45), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 450), 81)*49)) + (floormod((floordiv((threadIdx.x_1*4), 9) + 5), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 451)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 46), 81)) && (floormod(((threadIdx.x_1*4) + 46), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 451), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 46), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 672)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 24), 81)) && (floormod(((threadIdx.x_1*4) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 672), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 24), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 673)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 25), 81)) && (floormod(((threadIdx.x_1*4) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 673), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 25), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 674)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 26), 81)) && (floormod(((threadIdx.x_1*4) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 674), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 26), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 675)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 9) + 3), 9)) && (floormod(((threadIdx.x_1*4) + 27), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 675), 81)*49)) + (floormod((floordiv((threadIdx.x_1*4), 9) + 3), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 896)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 5), 81)) && (floormod(((threadIdx.x_1*4) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 896), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 897)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 6), 81)) && (floormod(((threadIdx.x_1*4) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 897), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 898)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 7), 81)) && (floormod(((threadIdx.x_1*4) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 898), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 899)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 8), 81)) && (floormod(((threadIdx.x_1*4) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 899), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1120)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 67), 81)) && (floormod(((threadIdx.x_1*4) + 67), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1120), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 67), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1121)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 68), 81)) && (floormod(((threadIdx.x_1*4) + 68), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1121), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 68), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1122)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 69), 81)) && (floormod(((threadIdx.x_1*4) + 69), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1122), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 69), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1123)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 70), 81)) && (floormod(((threadIdx.x_1*4) + 70), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1123), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 70), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3080)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3192)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3192), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3248), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3304)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3304), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((blockIdx.x*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3416)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3472), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3528), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3640)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3696), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3752)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3864)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3864), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3976)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3976), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4088)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4144), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4200)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4200), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4368), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4424)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4536)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4536), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4592), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 4) {
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
}
}
}
@@ -771,7 +1005,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.352 ms
+ Execution time of this operator: 0.391 ms
@@ -820,36 +1054,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -868,14 +1102,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -893,430 +1127,619 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[28];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((9 <= ((((int)threadIdx.x) * 4) % 81)) && (((((int)threadIdx.x) * 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 81) * 49)) + ((((((int)threadIdx.x) * 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((9 <= (((((int)threadIdx.x) * 4) + 1) % 81)) && ((((((int)threadIdx.x) * 4) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((9 <= (((((int)threadIdx.x) * 4) + 2) % 81)) && ((((((int)threadIdx.x) * 4) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((9 <= (((((int)threadIdx.x) * 4) + 3) % 81)) && ((((((int)threadIdx.x) * 4) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 224)] = (((((9 <= (((((int)threadIdx.x) * 4) + 62) % 81)) && ((((((int)threadIdx.x) * 4) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 224) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 225)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 4) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 225) / 81) * 49)) + (((((((int)threadIdx.x) * 4) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 226)] = (((((9 <= (((((int)threadIdx.x) * 4) + 64) % 81)) && ((((((int)threadIdx.x) * 4) + 64) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 226) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 64) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 227)] = (((((9 <= (((((int)threadIdx.x) * 4) + 65) % 81)) && ((((((int)threadIdx.x) * 4) + 65) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 227) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 65) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 448)] = (((((9 <= (((((int)threadIdx.x) * 4) + 43) % 81)) && ((((((int)threadIdx.x) * 4) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 448) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 43) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 449)] = (((((9 <= (((((int)threadIdx.x) * 4) + 44) % 81)) && ((((((int)threadIdx.x) * 4) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 449) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 44) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 450)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 9) + 5) % 9)) && ((((((int)threadIdx.x) * 4) + 45) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 450) / 81) * 49)) + (((((((int)threadIdx.x) * 4) / 9) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 451)] = (((((9 <= (((((int)threadIdx.x) * 4) + 46) % 81)) && ((((((int)threadIdx.x) * 4) + 46) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 451) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 46) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 672)] = (((((9 <= (((((int)threadIdx.x) * 4) + 24) % 81)) && ((((((int)threadIdx.x) * 4) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 672) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 24) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 673)] = (((((9 <= (((((int)threadIdx.x) * 4) + 25) % 81)) && ((((((int)threadIdx.x) * 4) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 673) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 25) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 674)] = (((((9 <= (((((int)threadIdx.x) * 4) + 26) % 81)) && ((((((int)threadIdx.x) * 4) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 674) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 26) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 675)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 9) + 3) % 9)) && ((((((int)threadIdx.x) * 4) + 27) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 675) / 81) * 49)) + (((((((int)threadIdx.x) * 4) / 9) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 896)] = (((((9 <= (((((int)threadIdx.x) * 4) + 5) % 81)) && ((((((int)threadIdx.x) * 4) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 896) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 897)] = (((((9 <= (((((int)threadIdx.x) * 4) + 6) % 81)) && ((((((int)threadIdx.x) * 4) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 897) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 898)] = (((((9 <= (((((int)threadIdx.x) * 4) + 7) % 81)) && ((((((int)threadIdx.x) * 4) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 898) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 899)] = (((((9 <= (((((int)threadIdx.x) * 4) + 8) % 81)) && ((((((int)threadIdx.x) * 4) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 899) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1120)] = (((((9 <= (((((int)threadIdx.x) * 4) + 67) % 81)) && ((((((int)threadIdx.x) * 4) + 67) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1120) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 67) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1121)] = (((((9 <= (((((int)threadIdx.x) * 4) + 68) % 81)) && ((((((int)threadIdx.x) * 4) + 68) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1121) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 68) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1122)] = (((((9 <= (((((int)threadIdx.x) * 4) + 69) % 81)) && ((((((int)threadIdx.x) * 4) + 69) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1122) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 69) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1123)] = (((((9 <= (((((int)threadIdx.x) * 4) + 70) % 81)) && ((((((int)threadIdx.x) * 4) + 70) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1123) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 70) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 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) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 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)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 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) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 3080)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3192)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3304)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3304) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 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)];
+ kernel_shared[(((int)threadIdx.x) + 3416)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3640)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3752)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3864)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3864) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3976)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3976) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4088)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4200)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4200) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4424)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4424) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4536)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4592) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -1378,7 +1801,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 35.326 seconds)
+ **Total running time of the script:** ( 2 minutes 38.212 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 1ae78c693..3af012382 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)
- 9.6971 9.7140 9.7200 9.6574 0.0282
+ 9.7472 9.7564 9.7623 9.7229 0.0173
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 35083f615..6dd4fa15e 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)
- 752.1354 752.4016 752.4102 751.5943 0.3826
+ 753.2252 753.4355 753.9080 752.3320 0.6604
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.799 seconds)
+ **Total running time of the script:** ( 1 minutes 20.692 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 593e135a9..77bcd509f 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
@@ -397,16 +397,15 @@ 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_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer: int32, 0, 4) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (i.outer.inner: int32, 0, 2) {
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
{
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ 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
@@ -424,12 +423,12 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_19: int32 = (((i0.outer*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
let cse_var_17: int32 = (cse_var_18 + 9)
let cse_var_16: int32 = (cse_var_18 + 8)
let cse_var_15: int32 = (cse_var_18 + 7)
@@ -467,11 +466,9 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
}
- for (i0.inner: int32, 0, 32) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = ((((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -527,7 +524,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.711 ms
+ Execution time of this operator: 1.858 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 cb5defed3..713c3d460 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
@@ -5,16 +5,16 @@
Computation times
=================
-**00:43.677** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.066** 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``) | 00:43.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.031 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.025 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.008 | 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_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 |
++--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.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 c3b4a78ae..3cd8365d6 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
@@ -892,8 +892,8 @@ 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, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 97.00/97.00 result: MeasureResult(costs=(0.0023865407083333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8079521656036377, timestamp=1657667003.1451056) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 103.41/103.41 result: MeasureResult(costs=(0.0022385767083333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6624605655670166, timestamp=1657667899.0197847) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/103.41 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
@@ -1016,7 +1016,7 @@ 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, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/103.41 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
@@ -1139,7 +1139,7 @@ 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, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/103.41 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
@@ -1262,7 +1262,7 @@ 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, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/103.41 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
@@ -1280,7 +1280,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/103.41 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
@@ -1403,7 +1403,7 @@ 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, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/103.41 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
@@ -1526,7 +1526,7 @@ 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, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/103.41 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
@@ -1649,7 +1649,7 @@ 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, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/103.41 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
@@ -1772,7 +1772,7 @@ 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, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/103.41 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
@@ -1895,7 +1895,7 @@ 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, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/103.41 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
@@ -2018,7 +2018,7 @@ 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, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/103.41 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
@@ -2141,7 +2141,7 @@ 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, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/103.41 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
@@ -2264,7 +2264,7 @@ 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, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/103.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2352,7 +2352,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fdc40c70fa2
+ 12: 0x00007f2f78db2fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2417,7 +2417,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.73/144.73 result: MeasureResult(costs=(0.00159954444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4048492908477783, timestamp=1657667029.568814) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 144.13/144.13 result: MeasureResult(costs=(0.00160622003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4498698711395264, timestamp=1657667925.618543) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2474,7 +2474,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
- Time cost of this operator: 0.001962
+ Time cost of this operator: 0.001984
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 326312b10..7dcf14bfc 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 310.2 98.713 (1, 2, 10, 10, 3) 2 1 [310.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.981 (1, 6, 10, 10) 1 1 [3.082]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.306 (1, 1, 10, 10, 3) 1 1 [0.961]
- Total_time - 314.243 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.9 98.73 (1, 2, 10, 10, 3) 2 1 [308.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.018 0.965 (1, 6, 10, 10) 1 1 [3.018]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.306 (1, 1, 10, 10, 3) 1 1 [0.956]
+ Total_time - 312.874 - - - - -
@@ -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 80.5 96.713 (1, 6, 10, 10, 1) 2 1 [80.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 2.126 (1, 6, 10, 10) 1 1 [1.77]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.161 (1, 1, 10, 10, 3) 1 1 [0.967]
- Total_time - 83.236 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 87.688 96.439 (1, 6, 10, 10, 1) 2 1 [87.688]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.281 2.508 (1, 6, 10, 10) 1 1 [2.281]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 1.052 (1, 1, 10, 10, 3) 1 1 [0.957]
+ Total_time - 90.925 - - - - -
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 15869b0bb..0c6fd94e9 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/tmpfy2jac6e/images/random'
+ '/tmp/tmpaisq2qu8/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpfy2jac6e/images/target contains 8144 images
- /tmp/tmpfy2jac6e/images/random contains 5000 images
+ /tmp/tmpaisq2qu8/images/target contains 8144 images
+ /tmp/tmpaisq2qu8/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: 0.2115 - accuracy: 0.9239 - val_loss: 0.1373 - val_accuracy: 0.9539
+ 328/328 - 55s - loss: 0.2160 - accuracy: 0.9263 - val_loss: 0.2027 - val_accuracy: 0.9486
Epoch 2/3
- 328/328 - 52s - loss: 0.1027 - accuracy: 0.9617 - val_loss: 0.1240 - val_accuracy: 0.9615
+ 328/328 - 52s - loss: 0.0984 - accuracy: 0.9627 - val_loss: 0.1408 - val_accuracy: 0.9626
Epoch 3/3
- 328/328 - 52s - loss: 0.0644 - accuracy: 0.9762 - val_loss: 0.1382 - val_accuracy: 0.9603
+ 328/328 - 52s - loss: 0.0644 - accuracy: 0.9771 - val_loss: 0.1682 - val_accuracy: 0.9596
- <keras.callbacks.History object at 0x7f8a95194750>
+ <keras.callbacks.History object at 0x7f8a01075cd0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 43.425 seconds)
+ **Total running time of the script:** ( 4 minutes 56.932 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 57003c2b4..66cb24255 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
@@ -5,14 +5,14 @@
Computation times
=================
-**05:30.471** total execution time for **how_to_work_with_microtvm** files:
+**05:43.790** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:43.425 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:56.932 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.813 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:43.266 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.231 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.589 | 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 06111baad..dbc90903c 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:11.190** total execution time for **how_to_work_with_relay** files:
+**00:11.319** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.790 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.434 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.522 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 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 45338a456..cd930f383 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 0x7f8a19d87b90>
+ <function my_cuda_math_rule at 0x7f892fa1b290>
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 f2c2c1acf..790eedb67 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
=================
-**00:03.957** total execution time for **how_to_work_with_schedules** files:
+**00:04.077** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.825 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.904 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.948 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.956 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.510 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.525 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.500 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.512 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.103 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.036 | 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_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.014 | 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 704403a8e..bac6a9ab4 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/tmp35s4lpxn/input0.cc'\nsource_filename = \"/tmp/tmp35s4lpxn/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/tmpidqrvcss/input0.cc'\nsource_filename = \"/tmp/tmpidqrvcss/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 ac7e21e96..107c48eec 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
=================
-**00:20.482** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.281** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.476 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.274 | 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 7fffdbef2..4e1fc91fa 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 22.13s!
+ resnet18_v1 inference graph built in 23.11s!
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 439bae64f..ac2589218 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 15.54s!
+ yolov3-tiny inference graph built in 16.18s!
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 9e124c88b..7bf480a8a 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
=================
-**01:30.1000** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.468** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.395 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.832 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.604 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.636 | 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 4f98074f6..0ac34cf4c 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
=================
-**00:03.227** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.255** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.847 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.861 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.381 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.394 | 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 7d95663bd..6661a55f2 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
=================
-**00:00.694** total execution time for **topic_vta_tutorials** files:
+**00:00.726** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.374 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.389 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.320 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.337 | 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 8cee32c79..ec6b8719a 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: 93.143 ms
+ Execution time of this operator: 94.181 ms
@@ -451,11 +444,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 6.310 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 60df27cda..5a4989c6f 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.20/10.20 result: MeasureResult(costs=(0.026308889799999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.550269365310669, timestamp=1657665896.690626) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.94/10.20 result: MeasureResult(costs=(0.0911913238,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6053979396820068, timestamp=1657665898.822617) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.91/11.91 result: MeasureResult(costs=(0.0225477712,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5903007984161377, timestamp=1657665899.3881047) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.86/11.91 result: MeasureResult(costs=(0.1442380234,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.426532030105591, timestamp=1657665902.3726697) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.63/11.91 result: MeasureResult(costs=(0.0739211944,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3136017322540283, timestamp=1657665903.81545) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.83/11.91 result: MeasureResult(costs=(0.14700671059999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.508837938308716, timestamp=1657665906.371537) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.91 result: MeasureResult(costs=(0.3096179072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0711963176727295, timestamp=1657665911.995813) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.91/11.91 result: MeasureResult(costs=(0.024597503599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5300536155700684, timestamp=1657665912.550901) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.91/11.91 result: MeasureResult(costs=(0.140377322,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.346247434616089, timestamp=1657665915.0163388) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.80/11.91 result: MeasureResult(costs=(0.0957474934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6310820579528809, timestamp=1657665916.7078264) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.68/10.68 result: MeasureResult(costs=(0.0251438304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5358102321624756, timestamp=1657666747.4988713) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.94/10.68 result: MeasureResult(costs=(0.0914487968,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6139345169067383, timestamp=1657666749.1269186) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228150278,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5551362037658691, timestamp=1657666750.1854837) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.86/11.77 result: MeasureResult(costs=(0.1444526382,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4267220497131348, timestamp=1657666753.1907682) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.65/11.77 result: MeasureResult(costs=(0.07345220259999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3179502487182617, timestamp=1657666754.634562) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.85/11.77 result: MeasureResult(costs=(0.144810075,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4473183155059814, timestamp=1657666757.6450222) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.77 result: MeasureResult(costs=(0.3069856904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.027846336364746, timestamp=1657666762.7200606) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.61/11.77 result: MeasureResult(costs=(0.025293498600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5456364154815674, timestamp=1657666763.287901) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.76/11.77 result: MeasureResult(costs=(0.1523747024,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.537768840789795, timestamp=1657666765.9451177) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.78/11.77 result: MeasureResult(costs=(0.0964801614,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6493351459503174, timestamp=1657666767.6546364) [('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 77eb8e20d..294be36b0 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': 490.5165505800005, 'median': 490.57635289998416, 'std': 0.6108741252041227}
+ {'mean': 497.7452073199993, 'median': 497.59541724999394, 'std': 0.7735339599357726}
@@ -563,31 +563,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"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: 17.54/ 17.54 GFLOPS | Progress: (4/20) | 6.20 s
[Task 1/25] Current/Best: 6.17/ 17.54 GFLOPS | Progress: (8/20) | 9.20 s
[Task 1/25] Current/Best: 11.53/ 22.75 GFLOPS | Progress: (12/20) | 11.61 s
[Task 1/25] Current/Best: 16.84/ 22.83 GFLOPS | Progress: (16/20) | 13.29 s
[Task 1/25] Current/Best: 11.61/ 23.87 GFLOPS | Progress: (20/20) | 15.03 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.27/ 12.91 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 14.10/ 18.76 GFLOPS | Progress: (8/20) | 5.02 s
[Task 2/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (12/20) | 6.35 s
[Task 2/25] Current/Best: 12.63/ 20.46 GFLOPS | Progress: (16/20) | 7.61 s
[Task 2/25] Current/Best: 19.56/ 20.46 GFLOPS | Progress: (20/20) | 9.21 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/ 10.61 GFLOPS | Progress: (4/20) | 5.82 s
[Task 3/25] Current/Best: 15.55/ 16.83 GFLOPS | Progress: (8/20) | 7.72 s
[Task 3/25] Current/Best: 14.95/ 16.83 GFLOPS | Progress: (12/20) | 9.44 s
[Task 3/25] Current/Best: 7.16/ 23.75 GFLOPS | Progress: (16/20) | 11.35 s
[Task 3/25] Current/Best: 12.63/ 23.75 GFLOPS | Progress: (20/20) | 15.84 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.46/ 19.99 GFLOPS | Progress: (4/20) | 2.38 s
[Task 4/25] Current/Best: 6.85/ 19.99 GFLOPS | Progress: (8/20) | 6.68 s
[Task 4/25] Current/Best: 22.48/ 22.48 GFLOPS | Progress: (12/20) | 11.16 s
[Task 4/25] Current/Best: 17.42/ 22.48 GFLOPS | Progress: (16/20) | 13.37 s
[Task 4/25] Current/Best: 13.57/ 22.48 GFLOPS | Progress: (20/20) | 15.35 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.86/ 10.51 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.90/ 12.78 GFLOPS | Progress: (8/20) | 4.59 s
[Task 5/25] Current/Best: 11.60/ 18.11 GFLOPS | Progress: (12/20) | 7.66 s
[Task 5/25] Current/Best: 11.89/ 22.71 GFLOPS | Progress: (16/20) | 9.10 s
[Task 5/25] Current/Best: 12.14/ 22.71 GFLOPS | Progress: (20/20) | 10.93 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.46 GFLOPS | Progress: (4/20) | 3.95 s
[Task 6/25] Current/Best: 19.03/ 20.46 GFLOPS | Progress: (8/20) | 5.69 s
[Task 6/25] Current/Best: 13.33/ 20.46 GFLOPS | Progress: (12/20) | 7.59 s
[Task 6/25] Current/Best: 20.05/ 20.46 GFLOPS | Progress: (16/20) | 9.81 s
[Task 6/25] Current/Best: 3.73/ 20.46 GFLOPS | Progress: (20/20) | 12.35 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.16/ 12.92 GFLOPS | Progress: (4/20) | 3.58 s
[Task 7/25] Current/Best: 20.17/ 21.08 GFLOPS | Progress: (8/20) | 5.08 s
[Task 7/25] Current/Best: 11.00/ 21.08 GFLOPS | Progress: (12/20) | 7.08 s
[Task 7/25] Current/Best: 12.29/ 21.08 GFLOPS | Progress: (16/20) | 9.10 s
[Task 7/25] Current/Best: 6.40/ 21.81 GFLOPS | Progress: (20/20) | 11.54 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.05/ 14.12 GFLOPS | Progress: (4/20) | 2.89 s
[Task 8/25] Current/Best: 9.68/ 14.12 GFLOPS | Progress: (8/20) | 7.52 s
[Task 8/25] Current/Best: 12.75/ 14.12 GFLOPS | Progress: (12/20) | 13.52 s
[Task 8/25] Current/Best: 18.78/ 18.78 GFLOPS | Progress: (16/20) | 15.60 s
[Task 8/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (20/20) | 22.02 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/ 15.73 GFLOPS | Progress: (4/20) | 11.92 s
[Task 9/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (8/20) | 13.69 s
[Task 9/25] Current/Best: 8.30/ 23.46 GFLOPS | Progress: (12/20) | 16.00 s
[Task 9/25] Current/Best: 18.00/ 23.46 GFLOPS | Progress: (16/20) | 18.64 s
[Task 9/25] Current/Best: 9.11/ 23.46 GFLOPS | Progress: (20/20) | 26.11 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) | 2.51 s
[Task 10/25] Current/Best: 15.54/ 18.28 GFLOPS | Progress: (8/20) | 4.08 s
[Task 10/25] Current/Best: 12.82/ 18.28 GFLOPS | Progress: (12/20) | 5.60 s
[Task 10/25] Current/Best: 19.19/ 20.47 GFLOPS | Progress: (16/20) | 6.69 s
[Task 10/25] Current/Best: 8.89/ 20.47 GFLOPS | Progress: (20/20
) | 8.21 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/ 18.18 GFLOPS | Progress: (4/20) | 3.23 s
[Task 11/25] Current/Best: 16.89/ 18.18 GFLOPS | Progress: (8/20) | 5.93 s
[Task 11/25] Current/Best: 18.29/ 18.29 GFLOPS | Progress: (12/20) | 7.93 s
[Task 11/25] Current/Best: 13.26/ 21.15 GFLOPS | Progress: (16/20) | 10.66 s
[Task 11/25] Current/Best: 19.39/ 21.45 GFLOPS | Progress: (20/20) | 12.67 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/ 18.08 GFLOPS | Progress: (4/20) | 5.27 s
[Task 12/25] Current/Best: 5.29/ 18.08 GFLOPS | Progress: (8/20) | 8.93 s
[Task 12/25] Current/Best: 18.85/ 18.85 GFLOPS | Progress: (12/20) | 10.92 s
[Task 12/25] Current/Best: 15.56/ 18.85 GFLOPS | Progress: (16/20) | 13.64 s
[Task 12/25] Current/Best: 15.11/ 19.11 GFLOPS | Progress: (20/20) | 15.54 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.77/ 17.37 GFLOPS | Progress: (4/20) | 3.60 s
[Task 13/25] Current/Best: 16.12/ 21.01 GFLOPS | Progress: (8/20) | 5.99 s
[Task 13/25] Current/Best: 19.55/ 21.52 GFLOPS | Progress: (12/20) | 8.83 s
[Task 13/25] Current/Best: 12.24/ 21.52 GFLOPS | Progress: (16/20) | 12.20 s
[Task 13/25] Current/Best: 18.94/ 21.52 GFLOPS | Progress: (20/20) | 14.48 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.55/ 13.55 GFLOPS | Progress: (4/20) | 3.35 s
[Task 14/25] Current/Best: 6.13/ 13.55 GFLOPS | Progress: (8/20) | 5.54 s
[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 8.07 s
[Task 14/25] Current/Best: 16.61/ 20.49 GFLOPS | Progress: (16/20) | 9.70 s Done.
-
[Task 14/25] Current/Best: 17.49/ 20.49 GFLOPS | Progress: (20/20) | 11.44 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.18/ 17.61 GFLOPS | Progress: (4/20) | 2.68 s
[Task 15/25] Current/Best: 14.54/ 18.01 GFLOPS | Progress: (8/20) | 3.96 s
[Task 15/25] Current/Best: 10.37/ 22.16 GFLOPS | Progress: (12/20) | 6.08 s
[Task 15/25] Current/Best: 20.26/ 22.16 GFLOPS | Progress: (16/20) | 9.44 s
[Task 15/25] Current/Best: 9.69/ 22.16 GFLOPS | Progress: (20/20) | 10.45 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (4/20) | 2.92 s
[Task 16/25] Current/Best: 3.04/ 20.49 GFLOPS | Progress: (8/20) | 4.52 s
[Task 16/25] Current/Best: 19.65/ 20.49 GFLOPS | Progress: (12/20) | 5.72 s
[Task 16/25] Current/Best: 17.68/ 20.49 GFLOPS | Progress: (16/20) |
7.07 s
[Task 16/25] Current/Best: 10.03/ 22.32 GFLOPS | Progress: (20/20) | 9.11 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.23/ 18.72 GFLOPS | Progress: (4/20) | 4.69 s
[Task 17/25] Current/Best: 14.31/ 23.38 GFLOPS | Progress: (8/20) | 7.44 s
[Task 17/25] Current/Best: 16.63/ 23.38 GFLOPS | Progress: (12/20) | 9.46 s
[Task 17/25] Current/Best: 16.48/ 23.38 GFLOPS | Progress: (16/20) | 11.58 s
[Task 17/25] Current/Best: 10.04/ 23.38 GFLOPS | Progress: (20/20) | 13.69 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.35/ 17.94 GFLOPS | Progress: (4/20) | 3.64 s
[Task 18/25] Current/Best: 10.59/ 17.94 GFLOPS | Progress: (8/20) | 7.06 s
[Task 18/25] Current/Best: 19.36/ 19.36 GFLOPS | Progress: (12/20) | 8.97 s
[Task 18/25] Current/Best: 10.11/ 19.36 GFLOPS | Progress: (16/20) | 12.45 s
[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 13.98 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.17/ 20.45 GFLOPS | Progress: (4/20) | 5.94 s
[Task 19/25] Current/Best: 2.60/ 20.45 GFLOPS | Progress: (8/20) | 9.23 s
[Task 19/25] Current/Best: 19.63/ 21.53 GFLOPS | Progress: (12/20) | 11.99 s
[Task 19/25] Current/Best: 15.47/ 22.14 GFLOPS | Progress: (16/20) | 14.77 s
[Task 19/25] Current/Best: 2.70/ 23.72 GFLOPS | Progress: (20/20) | 17.62 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.37/ 15.08 GFLOPS | Progress: (4/20) | 3.25 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (4/20) | 6.33 s
[Task 1/25] Current/Best: 6.14/ 17.45 GFLOPS | Progress: (8/20) | 9.35 s
[Task 1/25] Current/Best: 11.52/ 22.66 GFLOPS | Progress: (12/20) | 11.79 s
[Task 1/25] Current/Best: 16.78/ 22.69 GFLOPS | Progress: (16/20) | 13.48 s
[Task 1/25] Current/Best: 11.58/ 23.71 GFLOPS | Progress: (20/20) | 15.25 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.16/ 12.89 GFLOPS | Progress: (4/20) | 3.85 s
[Task 2/25] Current/Best: 13.59/ 18.47 GFLOPS | Progress: (8/20) | 5.14 s
[Task 2/25] Current/Best: 21.06/ 21.06 GFLOPS | Progress: (12/20) | 6.49 s
[Task 2/25] Current/Best: 12.22/ 21.06 GFLOPS | Progress: (16/20) | 7.75 s
[Task 2/25] Current/Best: 19.19/ 21.06 GFLOPS | Progress: (20/20) | 9.31 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/ 10.39 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.32/ 16.88 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.88/ 16.88 GFLOPS | Progress: (12/20) | 9.60 s
[Task 3/25] Current/Best: 7.18/ 23.68 GFLOPS | Progress: (16/20) | 11.51 s
[Task 3/25] Current/Best: 12.56/ 23.68 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: 9.57/ 20.40 GFLOPS | Progress: (4/20) | 2.42 s
[Task 4/25] Current/Best: 6.85/ 20.40 GFLOPS | Progress: (8/20) | 6.80 s
[Task 4/25] Current/Best: 21.47/ 21.47 GFLOPS | Progress: (12/20) | 11.30 s
[Task 4/25] Current/Best: 17.28/ 21.47 GFLOPS | Progress: (16/20) | 13.56 s
[Task 4/25] Current/Best: 13.04/ 21.47 GFLOPS | Progress: (20/20) | 15.60 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.64/ 10.05 GFLOPS | Progress: (4/20) | 2.63 s
[Task 5/25] Current/Best: 11.70/ 12.82 GFLOPS | Progress: (8/20) | 4.70 s
[Task 5/25] Current/Best: 10.42/ 18.06 GFLOPS | Progress: (12/20) | 7.81 s
[Task 5/25] Current/Best: 11.62/ 22.36 GFLOPS | Progress: (16/20) | 9.24 s
[Task 5/25] Current/Best: 11.73/ 22.36 GFLOPS | Progress: (20/20) | 11.12 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.28/ 20.56 GFLOPS | Progress: (4/20) | 4.03 s
[Task 6/25] Current/Best: 18.96/ 20.56 GFLOPS | Progress: (8/20) | 5.81 s
[Task 6/25] Current/Best: 13.28/ 20.56 GFLOPS | Progress: (12/20) | 7.73 s
[Task 6/25] Current/Best: 19.91/ 20.56 GFLOPS | Progress: (16/20) | 9.99 s
[Task 6/25] Current/Best: 3.73/ 20.56 GFLOPS | Progress: (20/20) | 12.51 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.13/ 12.74 GFLOPS | Progress: (4/20) | 3.64 s
[Task 7/25] Current/Best: 20.10/ 21.16 GFLOPS | Progress: (8/20) | 5.15 s
[Task 7/25] Current/Best: 15.87/ 21.16 GFLOPS | Progress: (12/20) | 7.08 s
[Task 7/25] Current/Best: 12.21/ 21.16 GFLOPS | Progress: (16/20) | 9.14 s
[Task 7/25] Current/Best: 6.31/ 21.61 GFLOPS | Progress: (20/20) | 11.60 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.22/ 14.51 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.76/ 14.51 GFLOPS | Progress: (8/20) | 7.68 s
[Task 8/25] Current/Best: 12.83/ 14.51 GFLOPS | Progress: (12/20) | 13.91 s
[Task 8/25] Current/Best: 18.94/ 18.94 GFLOPS | Progress: (16/20) | 16.02 s
[Task 8/25] Current/Best: 20.05/ 20.05 GFLOPS | Progress: (20/20) | 22.63 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.26/ 15.76 GFLOPS | Progress: (4/20) | 12.00 s
[Task 9/25] Current/Best: 23.25/ 23.25 GFLOPS | Progress: (8/20) | 13.82 s
[Task 9/25] Current/Best: 8.23/ 23.25 GFLOPS | Progress: (12/20) | 16.23 s
[Task 9/25] Current/Best: 17.86/ 23.25 GFLOPS | Progress: (16/20) | 18.83 s
[Task 9/25] Current/Best: 8.97/ 23.25 GFLOPS | Progress: (20/20) | 26.67 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 2.57 s
[Task 10/25] Current/Best: 15.50/ 18.22 GFLOPS | Progress: (8/20) | 4.18 s
[Task 10/25] Current/Best: 12.52/ 19.02 GFLOPS | Progress: (12/20) | 5.72 s
[Task 10/25] Current/Best: 19.10/ 20.27 GFLOPS | Progress: (16/20) | 6.83 s
[Task 10/25] Current/Best: 8.95/ 20.27 GFLOPS | Progress: (20/20
) | 8.40 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/ 18.13 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.86/ 18.13 GFLOPS | Progress: (8/20) | 6.05 s
[Task 11/25] Current/Best: 17.97/ 18.13 GFLOPS | Progress: (12/20) | 8.12 s
[Task 11/25] Current/Best: 12.87/ 21.20 GFLOPS | Progress: (16/20) | 10.95 s
[Task 11/25] Current/Best: 19.18/ 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: 7.78/ 17.98 GFLOPS | Progress: (4/20) | 5.46 s
[Task 12/25] Current/Best: 5.25/ 17.98 GFLOPS | Progress: (8/20) | 9.21 s
[Task 12/25] Current/Best: 19.01/ 19.01 GFLOPS | Progress: (12/20) | 11.21 s
[Task 12/25] Current/Best: 14.77/ 19.01 GFLOPS | Progress: (16/20) | 13.99 s
[Task 12/25] Current/Best: 15.22/ 19.28 GFLOPS | Progress: (20/20) | 15.90 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.91/ 17.32 GFLOPS | Progress: (4/20) | 3.70 s
[Task 13/25] Current/Best: 15.50/ 20.76 GFLOPS | Progress: (8/20) | 6.15 s
[Task 13/25] Current/Best: 19.38/ 21.15 GFLOPS | Progress: (12/20) | 9.07 s
[Task 13/25] Current/Best: 12.19/ 21.15 GFLOPS | Progress: (16/20) | 12.51 s
[Task 13/25] Current/Best: 18.74/ 21.15 GFLOPS | Progress: (20/20) | 14.75 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.49/ 13.49 GFLOPS | Progress: (4/20) | 3.37 s
[Task 14/25] Current/Best: 6.08/ 13.49 GFLOPS | Progress: (8/20) | 5.52 s
[Task 14/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (12/20) | 8.05 s
[Task 14/25] Current/Best: 16.84/ 20.53 GFLOPS | Progress: (16/20) | 9.70 s Done.
+
[Task 14/25] Current/Best: 16.99/ 20.53 GFLOPS | Progress: (20/20) | 11.46 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.15/ 17.66 GFLOPS | Progress: (4/20) | 2.74 s
[Task 15/25] Current/Best: 14.38/ 17.94 GFLOPS | Progress: (8/20) | 4.04 s
[Task 15/25] Current/Best: 10.29/ 22.08 GFLOPS | Progress: (12/20) | 6.13 s
[Task 15/25] Current/Best: 20.32/ 22.08 GFLOPS | Progress: (16/20) | 9.11 s
[Task 15/25] Current/Best: 9.68/ 22.08 GFLOPS | Progress: (20/20) | 10.08 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (4/20) | 2.97 s
[Task 16/25] Current/Best: 3.04/ 20.64 GFLOPS | Progress: (8/20) | 4.59 s
[Task 16/25] Current/Best: 19.62/ 20.64 GFLOPS | Progress: (12/20) | 5.82 s
[Task 16/25] Current/Best: 17.74/ 20.64 GFLOPS | Progress: (16/20) |
7.20 s
[Task 16/25] Current/Best: 9.98/ 22.16 GFLOPS | Progress: (20/20) | 9.27 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.44/ 18.83 GFLOPS | Progress: (4/20) | 4.74 s
[Task 17/25] Current/Best: 14.44/ 22.94 GFLOPS | Progress: (8/20) | 7.63 s
[Task 17/25] Current/Best: 16.86/ 22.94 GFLOPS | Progress: (12/20) | 9.70 s
[Task 17/25] Current/Best: 17.18/ 22.94 GFLOPS | Progress: (16/20) | 11.85 s
[Task 17/25] Current/Best: 10.04/ 22.94 GFLOPS | Progress: (20/20) | 13.98 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.12/ 18.22 GFLOPS | Progress: (4/20) | 3.75 s
[Task 18/25] Current/Best: 10.60/ 19.85 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 19.56/ 19.85 GFLOPS | Progress: (12/20) | 9.17 s
[Task 18/25] Current/Best: 9.86/ 19.85 GFLOPS | Progress: (16/20) | 12.75 s
[Task 18/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (20/20) | 14.27 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.48/ 20.20 GFLOPS | Progress: (4/20) | 6.20 s
[Task 19/25] Current/Best: 2.61/ 20.20 GFLOPS | Progress: (8/20) | 9.49 s
[Task 19/25] Current/Best: 19.34/ 20.82 GFLOPS | Progress: (12/20) | 12.27 s
[Task 19/25] Current/Best: 15.21/ 20.91 GFLOPS | Progress: (16/20) | 15.09 s
[Task 19/25] Current/Best: 2.70/ 23.23 GFLOPS | Progress: (20/20) | 17.86 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.09/ 15.01 GFLOPS | Progress: (4/20) | 3.36 s Done.
Done.
-
[Task 20/25] Current/Best: 9.67/ 15.08 GFLOPS | Progress: (8/20) | 6.68 s
[Task 20/25] Current/Best: 2.32/ 16.62 GFLOPS | Progress: (12/20) | 10.74 s
[Task 20/25] Current/Best: 12.50/ 16.62 GFLOPS | Progress: (16/20) | 14.42 s
[Task 20/25] Current/Best: 11.91/ 22.24 GFLOPS | Progress: (20/20) | 16.50 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.75 GFLOPS | Progress: (4/20) | 3.19 s
[Task 21/25] Current/Best: 14.62/ 17.75 GFLOPS | Progress: (8/20) | 4.76 s
[Task 21/25] Current/Best: 1.61/ 17.75 GFLOPS | Progress: (12/20) | 6.91 s
[Task 21/25] Current/Best: 16.74/ 17.75 GFLOPS | Progress: (16/20) | 10.33 s
[Task 21/25] Current/Best: 4.46/ 17.75 GFLOPS | Progress: (20/20) | 17.37 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.69/ 17.01 GFLOPS | Progress: (4/20
) | 2.66 s
[Task 22/25] Current/Best: 8.76/ 21.94 GFLOPS | Progress: (8/20) | 4.55 s
[Task 22/25] Current/Best: 19.88/ 21.94 GFLOPS | Progress: (12/20) | 6.83 s
[Task 22/25] Current/Best: 15.51/ 21.94 GFLOPS | Progress: (16/20) | 8.87 s
[Task 22/25] Current/Best: 13.40/ 21.94 GFLOPS | Progress: (20/20) | 10.52 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.52/ 20.79 GFLOPS | Progress: (4/20) | 3.21 s
[Task 23/25] Current/Best: 14.80/ 20.79 GFLOPS | Progress: (8/20) | 6.57 s
[Task 23/25] Current/Best: 21.03/ 21.80 GFLOPS | Progress: (12/20) | 8.39 s
[Task 23/25] Current/Best: 6.49/ 21.80 GFLOPS | Progress: (16/20) | 15.37 s
[Task 23/25] Current/Best: 7.99/ 21.80 GFLOPS | Progress: (20/20) | 19.57 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.36/ 8.36 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 3.62/ 8.36 GFLOPS | Progress: (8/20) | 23.00 s
[Task 24/25] Current/Best: 4.29/ 8.36 GFLOPS | Progress: (12/20) | 33.72 s Done.
+
[Task 20/25] Current/Best: 10.39/ 15.01 GFLOPS | Progress: (8/20) | 6.68 s
[Task 20/25] Current/Best: 2.32/ 16.89 GFLOPS | Progress: (12/20) | 10.63 s
[Task 20/25] Current/Best: 12.36/ 16.89 GFLOPS | Progress: (16/20) | 14.44 s
[Task 20/25] Current/Best: 13.46/ 21.66 GFLOPS | Progress: (20/20) | 16.57 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.63 GFLOPS | Progress: (4/20) | 3.25 s
[Task 21/25] Current/Best: 14.52/ 17.63 GFLOPS | Progress: (8/20) | 4.85 s
[Task 21/25] Current/Best: 1.61/ 17.63 GFLOPS | Progress: (12/20) | 7.02 s
[Task 21/25] Current/Best: 18.25/ 18.25 GFLOPS | Progress: (16/20) | 10.48 s
[Task 21/25] Current/Best: 4.47/ 18.25 GFLOPS | Progress: (20/20) | 17.72 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20
) | 2.70 s
[Task 22/25] Current/Best: 9.09/ 21.35 GFLOPS | Progress: (8/20) | 4.67 s
[Task 22/25] Current/Best: 19.96/ 21.35 GFLOPS | Progress: (12/20) | 7.01 s
[Task 22/25] Current/Best: 15.14/ 21.35 GFLOPS | Progress: (16/20) | 9.08 s
[Task 22/25] Current/Best: 15.11/ 21.35 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: 17.38/ 20.25 GFLOPS | Progress: (4/20) | 3.26 s
[Task 23/25] Current/Best: 15.68/ 20.25 GFLOPS | Progress: (8/20) | 6.61 s
[Task 23/25] Current/Best: 20.80/ 21.47 GFLOPS | Progress: (12/20) | 8.44 s
[Task 23/25] Current/Best: 6.05/ 21.47 GFLOPS | Progress: (16/20) | 15.63 s
[Task 23/25] Current/Best: 7.45/ 21.47 GFLOPS | Progress: (20/20) | 19.88 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.49/ 8.49 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 1.98/ 8.49 GFLOPS | Progress: (8/20) | 22.87 s
[Task 24/25] Current/Best: 4.13/ 8.49 GFLOPS | Progress: (12/20) | 34.40 s Done.
Done.
-
[Task 24/25] Current/Best: 6.30/ 8.84 GFLOPS | Progress: (16/20) | 39.14 s
[Task 24/25] Current/Best: 3.32/ 8.84 GFLOPS | Progress: (20/20) | 44.89 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/ 2.75 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 6.05/ 8.41 GFLOPS | Progress: (8/20) | 22.81 s
[Task 25/25] Current/Best: 5.99/ 8.41 GFLOPS | Progress: (12/20) | 34.08 s
[Task 25/25] Current/Best: 5.88/ 8.62 GFLOPS | Progress: (16/20) | 35.82 s
[Task 25/25] Current/Best: 2.85/ 9.13 GFLOPS | Progress: (20/20) | 46.52 s
+
[Task 24/25] Current/Best: 7.26/ 8.78 GFLOPS | Progress: (16/20) | 39.93 s
[Task 24/25] Current/Best: 3.30/ 8.81 GFLOPS | Progress: (20/20) | 45.94 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/ 2.87 GFLOPS | Progress: (4/20) | 11.62 s
[Task 25/25] Current/Best: 5.65/ 7.68 GFLOPS | Progress: (8/20) | 22.89 s
[Task 25/25] Current/Best: 5.81/ 7.68 GFLOPS | Progress: (12/20) | 34.38 s
[Task 25/25] Current/Best: 5.73/ 8.81 GFLOPS | Progress: (16/20) | 36.14 s
[Task 25/25] Current/Best: 2.91/ 8.81 GFLOPS | Progress: (20/20) | 46.81 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 407.724118860001, 'median': 407.08959275000325, 'std': 1.6335373221054401}
- unoptimized: {'mean': 490.5165505800005, 'median': 490.57635289998416, 'std': 0.6108741252041227}
+ optimized: {'mean': 413.3053585200014, 'median': 413.1602497500012, 'std': 0.8336720342995587}
+ unoptimized: {'mean': 497.7452073199993, 'median': 497.59541724999394, 'std': 0.7735339599357726}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 8.870 seconds)
+ **Total running time of the script:** ( 10 minutes 20.161 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 2d2b829f3..b809a6ebc 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
- 1.246e-07 secs/op
+ 1.3e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index e151ca258..b558618d5 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, 0xc6b6230)), stage(b, placeholder(b, 0x23811480)), 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, 0x17797c90)), stage(b, placeholder(b, 0xe3664a0)), 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 935566a89..124d7203d 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:05.304** total execution time for **tutorial** files:
+**13:08.679** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:08.870 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:20.161 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:06.310 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.950 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:57.801 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:54.573 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:27.610 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.276 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.402 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.600 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.679 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.266 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.493 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.695 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.132 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.150 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index e2b152ca2..d83b8a3d6 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: 0.000008
- naive: 0.000006
+ naive: 0.000009
@@ -403,7 +403,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000007
+ parallel: 0.000008
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.76066000071296e-06 1.0
- naive 5.8458e-06 0.7532606762134864
- parallel 7.073400000000001e-06 0.9114430988279577
- vector 2.4601100000000004e-05 3.1699752337739238
+ numpy 7.715100000496023e-06 1.0
+ naive 8.737599999999999e-06 1.1325323067022122
+ parallel 7.9954e-06 1.0363313501427014
+ vector 2.46161e-05 3.190639136034189
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017646
+ Numpy running time: 0.018400
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.193487
+ none: 3.315778
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.298100
+ blocking: 0.316005
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.329357
+ vectorization: 0.346390
@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:268: 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: 0.116926
+ loop permutation: 0.117841
@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:268: 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: 0.110517
+ array packing: 0.108889
@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:268: 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: 0.110604
+ block caching: 0.111655
@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:268: 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: 0.144750
+ parallelization: 0.145801
@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 3.1934868985000002 1.0
- blocking 0.2980997118 0.09334615148727217
- vectorization 0.32935668430000004 0.10313387678361882
- loop permutation 0.11692551800000002 0.036613745951148455
- array packing 0.1105171986 0.03460706184575568
- block caching 0.11060426679999999 0.034634326150500716
- parallelization 0.1447499224 0.045326605995468436
+ none 3.3157780973 1.0
+ blocking 0.3160050896 0.09530344924388014
+ vectorization 0.3463898833 0.10446714862555527
+ loop permutation 0.11784143039999999 0.03553960094493564
+ array packing 0.1088888424 0.032839604824178956
+ block caching 0.111655129 0.03367388459768146
+ parallelization 0.1458010669 0.043971901201327115
diff --git a/docs/commit_hash b/docs/commit_hash
index 5cb52c17a..48f4bae92 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-d07f2fb8056413cc844ce61a883bf4f51fd42848
+1d5d357d69ab8a0ceae047532ab778359676cda7
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 3315ffe58..cc491db17 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -569,7 +569,7 @@ 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 0.160 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.459 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 c3f1b4092..b4ec6f844 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ 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.zipdedc4325-5145-42e6-b6e6-cc9e05eb956a 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.zip49e85b8a-b60f-4ccc-8dff-5950c66cf008 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 c56947e7c..84b686224 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,13 +427,12 @@ 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, 78.9MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 56.9MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 55.8MB/s]
- 71%|#######1 | 29.5M/41.5M [00:00<00:00, 55.0MB/s]
- 84%|########4 | 34.9M/41.5M [00:00<00:00, 53.3MB/s]
- 96%|#########6| 40.0M/41.5M [00:00<00:00, 53.0MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 56.5MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 42.8MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 45.0MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 40.8MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 46.9MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 51.1MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 47.1MB/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 6db1b8b43..fc0da1371 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,8 +409,10 @@ 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]
- 43%|####3 | 19.3M/44.7M [00:00<00:00, 202MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 236MB/s]
+ 9%|9 | 4.10M/44.7M [00:00<00:00, 43.0MB/s]
+ 18%|#8 | 8.20M/44.7M [00:00<00:00, 41.7MB/s]
+ 63%|######3 | 28.2M/44.7M [00:00<00:00, 116MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 120MB/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 dee5d6df1..47327fc4e 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.251 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.133 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 f17e51d0a..c349285e7 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>04:54.746</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:18.936</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:03.251</p></td>
+<td><p>01:04.133</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:00.160</p></td>
+<td><p>01:01.459</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>00:39.171</p></td>
+<td><p>00:39.327</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>00:26.210</p></td>
+<tr class="row-even"><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>00:32.825</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.877</p></td>
+<tr class="row-odd"><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>00:25.874</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:23.301</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
+<td><p>00:25.555</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>00:22.852</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
+<td><p>00:25.249</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>00:18.888</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
+<td><p>00:23.021</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>00:13.660</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
+<td><p>00:19.118</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>00:02.376</p></td>
+<td><p>00:02.375</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 145f4ff4e..b45cec3f1 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.0698 15.7823 18.1002 15.7034 0.6941
+ 17.8958 16.2035 28.7124 16.1167 3.8020
</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 e5909adfb..441ee3409 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,13 +431,16 @@ 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]
- 11%|#1 | 19.3M/170M [00:00<00:00, 202MB/s]
- 26%|##6 | 44.6M/170M [00:00<00:00, 240MB/s]
- 41%|####1 | 69.9M/170M [00:00<00:00, 251MB/s]
- 56%|#####6 | 95.4M/170M [00:00<00:00, 257MB/s]
- 71%|#######1 | 121M/170M [00:00<00:00, 262MB/s]
- 86%|########6 | 147M/170M [00:00<00:00, 265MB/s]
-100%|##########| 170M/170M [00:00<00:00, 257MB/s]
+ 2%|1 | 3.34M/170M [00:00<00:04, 35.1MB/s]
+ 4%|3 | 6.77M/170M [00:00<00:04, 35.5MB/s]
+ 13%|#2 | 21.8M/170M [00:00<00:01, 91.4MB/s]
+ 28%|##7 | 47.5M/170M [00:00<00:00, 161MB/s]
+ 43%|####2 | 72.8M/170M [00:00<00:00, 199MB/s]
+ 54%|#####4 | 91.8M/170M [00:00<00:00, 184MB/s]
+ 65%|######5 | 111M/170M [00:00<00:00, 186MB/s]
+ 78%|#######7 | 132M/170M [00:00<00:00, 197MB/s]
+ 91%|#########1| 155M/170M [00:00<00:00, 208MB/s]
+100%|##########| 170M/170M [00:01<00:00, 177MB/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').
@@ -532,7 +535,7 @@ 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> ( 2 minutes 52.075 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 0.309 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 8536951a9..91a71252d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -475,7 +475,10 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 171MB/s]
+ 23%|##2 | 3.12M/13.6M [00:00<00:00, 32.6MB/s]
+ 55%|#####5 | 7.48M/13.6M [00:00<00:00, 40.3MB/s]
+ 88%|########7 | 11.9M/13.6M [00:00<00:00, 42.5MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 41.4MB/s]
</pre></div>
</div>
</div>
@@ -564,7 +567,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.2850 90.2593 91.3379 90.1044 0.1477
+ 90.4858 90.3755 94.1574 90.2464 0.4623
</pre></div>
</div>
<div class="admonition note">
@@ -603,7 +606,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.949 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.747 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 044b9f0f8..1a2615c42 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -568,7 +568,7 @@ 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)
- 118.6430 118.5980 121.1373 117.7792 0.3988
+ 122.1050 122.0081 124.2679 121.2033 0.4942
</pre></div>
</div>
<div class="admonition note">
@@ -596,7 +596,7 @@ 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 57.107 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 3.898 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 041ebf5fd..6438bdb59 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ 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 20.168 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.520 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 1dda93b76..dafaafb80 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,24 +436,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5744/132723 [00:00<00:02, 57433.76KB/s]
- 10%|# | 13424/132723 [00:00<00:01, 68822.10KB/s]
- 15%|#5 | 20307/132723 [00:00<00:01, 58900.41KB/s]
- 21%|##1 | 28339/132723 [00:00<00:01, 66572.00KB/s]
- 26%|##6 | 35163/132723 [00:00<00:02, 36370.13KB/s]
- 33%|###2 | 43222/132723 [00:00<00:01, 45549.53KB/s]
- 37%|###7 | 49306/132723 [00:01<00:03, 26536.74KB/s]
- 43%|####3 | 57225/132723 [00:01<00:02, 34446.29KB/s]
- 49%|####9 | 65453/132723 [00:01<00:01, 42897.01KB/s]
- 54%|#####4 | 71875/132723 [00:01<00:02, 29620.61KB/s]
- 60%|###### | 79969/132723 [00:02<00:01, 37474.29KB/s]
- 65%|######4 | 85876/132723 [00:02<00:01, 35662.82KB/s]
- 71%|####### | 93992/132723 [00:02<00:00, 43899.02KB/s]
- 77%|#######6 | 102013/132723 [00:02<00:00, 51358.64KB/s]
- 83%|########3 | 110165/132723 [00:02<00:00, 58202.16KB/s]
- 88%|########8 | 117233/132723 [00:02<00:00, 60097.65KB/s]
- 94%|#########4| 125219/132723 [00:02<00:00, 65145.33KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 46704.19KB/s]
+ 4%|4 | 5325/132723 [00:00<00:02, 53241.17KB/s]
+ 10%|# | 13279/132723 [00:00<00:01, 68705.52KB/s]
+ 16%|#6 | 21447/132723 [00:00<00:01, 74626.37KB/s]
+ 22%|##2 | 29562/132723 [00:00<00:01, 77199.94KB/s]
+ 28%|##8 | 37678/132723 [00:00<00:01, 78625.54KB/s]
+ 34%|###4 | 45677/132723 [00:00<00:01, 79087.41KB/s]
+ 40%|#### | 53586/132723 [00:00<00:01, 78944.61KB/s]
+ 46%|####6 | 61481/132723 [00:00<00:00, 78437.73KB/s]
+ 52%|#####2 | 69326/132723 [00:00<00:00, 78052.42KB/s]
+ 58%|#####8 | 77168/132723 [00:01<00:00, 78162.55KB/s]
+ 64%|######4 | 84985/132723 [00:01<00:00, 77926.86KB/s]
+ 70%|######9 | 92849/132723 [00:01<00:00, 78134.62KB/s]
+ 76%|#######5 | 100663/132723 [00:01<00:00, 78083.29KB/s]
+ 82%|########1 | 108498/132723 [00:01<00:00, 78160.92KB/s]
+ 88%|########7 | 116361/132723 [00:01<00:00, 78298.53KB/s]
+ 94%|#########3| 124192/132723 [00:01<00:00, 78256.36KB/s]
+100%|#########9| 132229/132723 [00:01<00:00, 78887.98KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 77449.18KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -496,7 +496,7 @@ 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 19.183 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 24.028 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 64ecdf340..d820b465d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>10:24.333</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:52.850</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</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>02:52.075</p></td>
+<td><p>03:00.309</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>02:19.183</p></td>
+<td><p>02:24.028</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>01:57.107</p></td>
+<td><p>02:03.898</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>01:20.168</p></td>
+<td><p>01:24.520</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>01:05.949</p></td>
+<td><p>01:08.747</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>00:28.249</p></td>
+<td><p>00:29.249</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:21.596</p></td>
+<td><p>00:22.092</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 39a969f56..31e16c431 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -607,7 +607,7 @@ 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.zip80654098-a492-46da-a9fe-3ca654536d48 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.zip8ec81053-9169-4f5a-87b9-d1cfb4ce2a2b 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>
@@ -671,7 +671,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 1a957d957..8331e88a5 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:39.436</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.939</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:36.373</p></td>
+<td><p>00:37.691</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>00:02.154</p></td>
+<td><p>00:02.302</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>00:00.901</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>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 0dc383293..2222b5cff 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ 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: 6497us [6497us] (45.62%; 45.62%)
-FoldScaleAxis: 7744us [6us] (54.38%; 54.38%)
- FoldConstant: 7739us [1563us] (54.34%; 99.93%)
- InferType: 6176us [6176us] (43.36%; 79.80%)
+InferType: 6718us [6718us] (45.51%; 45.51%)
+FoldScaleAxis: 8045us [6us] (54.49%; 54.49%)
+ FoldConstant: 8039us [1637us] (54.45%; 99.92%)
+ InferType: 6401us [6401us] (43.36%; 79.63%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ 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: 6152us [6152us] (44.62%; 44.62%)
-FoldScaleAxis: 7635us [5us] (55.38%; 55.38%)
- FoldConstant: 7630us [1594us] (55.35%; 99.94%)
- InferType: 6037us [6037us] (43.79%; 79.11%)
+InferType: 6297us [6297us] (44.12%; 44.12%)
+FoldScaleAxis: 7977us [5us] (55.88%; 55.88%)
+ FoldConstant: 7972us [1652us] (55.85%; 99.93%)
+ InferType: 6320us [6320us] (44.27%; 79.28%)
</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 738911f3a..774111aa0 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -559,7 +559,7 @@ 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: 48.468963 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 33.139916 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 f4ea05198..42dc1344a 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -901,7 +901,7 @@ 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: 6.852600 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.368312 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 da0762c77..14a44a3ea 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -456,8 +456,8 @@ 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: 0.018232
-Baseline: 3.196743
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019177
+Baseline: 3.343142
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -517,7 +517,7 @@ 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: 0.297766
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.318190
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -584,7 +584,7 @@ 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: 0.335953
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.349233
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -645,7 +645,7 @@ 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: 0.117141
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.121343
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -728,7 +728,7 @@ 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: 0.110547
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111546
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -814,7 +814,7 @@ 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: 0.110636
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112412
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -904,7 +904,7 @@ 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: 0.144786
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146764
</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 eca569ce1..697b7d3ab 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:33.732</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.955</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.442</p></td>
+<td><p>00:32.584</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>00:01.263</p></td>
+<td><p>00:01.364</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>00:01.026</p></td>
+<td><p>00:01.008</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 8b8cd7a5f..6f55a50eb 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>05:12.565</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:17.345</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</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>02:35.326</p></td>
+<td><p>02:38.212</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>01:19.799</p></td>
+<td><p>01:20.692</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>00:42.911</p></td>
+<td><p>00:43.640</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>00:17.715</p></td>
+<td><p>00:17.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.525</p></td>
+<td><p>00:08.693</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>00:08.288</p></td>
+<td><p>00:08.574</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 c258045aa..544e84124 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
@@ -486,483 +486,717 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [28]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[16] = 0f32
+ conv2d_nchw_1[20] = 0f32
+ conv2d_nchw_1[24] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ conv2d_nchw_1[17] = 0f32
+ conv2d_nchw_1[21] = 0f32
+ conv2d_nchw_1[25] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[14] = 0f32
+ conv2d_nchw_1[18] = 0f32
+ conv2d_nchw_1[22] = 0f32
+ conv2d_nchw_1[26] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*72)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
- }
- if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
- }
+ conv2d_nchw_1[15] = 0f32
+ conv2d_nchw_1[19] = 0f32
+ conv2d_nchw_1[23] = 0f32
+ conv2d_nchw_1[27] = 0f32
+ for (rc.outer.outer: int32, 0, 32) {
+ 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" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*4), 81)) && (floormod((threadIdx.x_1*4), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 81)*49)) + (floordiv(floormod((threadIdx.x_1*4), 81), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8 [...]
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 1), 81)) && (floormod(((threadIdx.x_1*4) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 2), 81)) && (floormod(((threadIdx.x_1*4) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 3), 81)) && (floormod(((threadIdx.x_1*4) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 224)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 62), 81)) && (floormod(((threadIdx.x_1*4) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 224), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 62), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 225)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 9) + 7), 9)) && (floormod(((threadIdx.x_1*4) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 225), 81)*49)) + (floormod((floordiv((threadIdx.x_1*4), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 226)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 64), 81)) && (floormod(((threadIdx.x_1*4) + 64), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 226), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 64), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 227)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 65), 81)) && (floormod(((threadIdx.x_1*4) + 65), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 227), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 65), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 448)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 43), 81)) && (floormod(((threadIdx.x_1*4) + 43), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 448), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 43), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 449)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 44), 81)) && (floormod(((threadIdx.x_1*4) + 44), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 449), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 44), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 450)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 9) + 5), 9)) && (floormod(((threadIdx.x_1*4) + 45), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 450), 81)*49)) + (floormod((floordiv((threadIdx.x_1*4), 9) + 5), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 451)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 46), 81)) && (floormod(((threadIdx.x_1*4) + 46), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 451), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 46), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 672)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 24), 81)) && (floormod(((threadIdx.x_1*4) + 24), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 672), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 24), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 673)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 25), 81)) && (floormod(((threadIdx.x_1*4) + 25), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 673), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 25), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 674)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 26), 81)) && (floormod(((threadIdx.x_1*4) + 26), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 674), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 26), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 675)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 9) + 3), 9)) && (floormod(((threadIdx.x_1*4) + 27), 81) < 72)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 675), 81)*49)) + (floormod((floordiv((threadIdx.x_1*4), 9) + 3), 9)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 896)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 5), 81)) && (floormod(((threadIdx.x_1*4) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 896), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 897)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 6), 81)) && (floormod(((threadIdx.x_1*4) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 897), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 898)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 7), 81)) && (floormod(((threadIdx.x_1*4) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 898), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 899)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 8), 81)) && (floormod(((threadIdx.x_1*4) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 899), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1120)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 67), 81)) && (floormod(((threadIdx.x_1*4) + 67), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1120), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 67), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dty [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1121)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 68), 81)) && (floormod(((threadIdx.x_1*4) + 68), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1121), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 68), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dty [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1122)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 69), 81)) && (floormod(((threadIdx.x_1*4) + 69), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1122), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 69), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dty [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1123)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*4) + 70), 81)) && (floormod(((threadIdx.x_1*4) + 70), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1123), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 70), 81), 9)*7)) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dty [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((blockIdx.x*147456) + cse_var_1) + (floordiv((threadIdx.x_2 + 56), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 112), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 168), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 280), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 336), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 504), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 560), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 616), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 672), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 728), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 840), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 952), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1064), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1232), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1288), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((blockIdx.x*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1400), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1456), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1512), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1624)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1624), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1680)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1680), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1736)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1736), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1848)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1848), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1904)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1904), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2072)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2072), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2128)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2128), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2184)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2184), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2296)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2296), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2408)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2408), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2520)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2520), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2576)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2576), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2632)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2632), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2688), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2800)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2800), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2856)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2856), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 2968)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2968), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3024)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3080)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3080), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3192)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3192), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3248)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3248), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3304)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3304), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[(((((blockIdx.x*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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3416)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3416), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3472)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3472), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3528), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3640)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3640), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3696)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3696), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3752)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3752), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3864)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3864), 144)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 3976)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3976), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((blockIdx.x*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4088)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4088), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4144)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4144), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4200)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4200), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4312), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 136), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4368)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4368), 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" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4424)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4424), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ 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), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 4536)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4536), 144)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 4592)] = kernel[(((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4592), 144)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[16] = (conv2d_nchw_1[16] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[20] = (conv2d_nchw_1[20] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[24] = (conv2d_nchw_1[24] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 144)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 153)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 162)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 171)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 180)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 189)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 198)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 207)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 216)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 225)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 234)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 243)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 252)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 261)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 270)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[17] = (conv2d_nchw_1[17] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[21] = (conv2d_nchw_1[21] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[25] = (conv2d_nchw_1[25] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 279)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 288)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 297)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 306)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 315)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 324)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 333)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 342)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 351)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 360)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 369)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 378)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 387)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 396)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 405)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 414)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[14] = (conv2d_nchw_1[14] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[18] = (conv2d_nchw_1[18] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[22] = (conv2d_nchw_1[22] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[26] = (conv2d_nchw_1[26] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 423)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 2)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 3)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 4)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 5)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 6)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 432)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 81)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 82)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 83)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 85)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 86)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 87)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 441)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 162)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 163)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 164)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 165)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 166)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 167)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 168)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 450)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 243)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 244)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 245)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 246)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 247)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 248)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 249)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 459)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 324)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 325)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 326)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 327)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 328)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 329)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 330)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 468)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 405)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 406)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 407)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 408)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 409)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 410)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 411)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 477)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 486)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 487)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 488)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 489)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 490)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 491)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 492)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 486)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 567)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 568)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 569)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 570)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 571)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 572)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 573)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 495)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 648)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 649)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 650)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 651)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 652)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 653)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 654)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 504)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 729)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 730)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 731)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 732)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 733)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 734)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 735)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 513)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 810)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 811)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 812)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 813)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 814)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 815)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 816)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 522)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 891)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 892)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 893)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 894)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 895)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 896)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 897)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 531)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 972)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 973)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 974)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 975)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 976)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 977)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 978)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 540)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1053)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1054)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1055)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1056)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1057)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1058)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1059)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 549)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1134)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1135)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1136)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1137)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1138)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1139)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1140)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 558)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1215)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1216)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1217)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[15] = (conv2d_nchw_1[15] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1218)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[19] = (conv2d_nchw_1[19] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1219)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[23] = (conv2d_nchw_1[23] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1220)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
+ conv2d_nchw_1[27] = (conv2d_nchw_1[27] + (pad_temp.shared_1[((((ry.outer.inner*9) + (floormod(threadIdx.x, 7)*9)) + rx.outer.inner) + 1221)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*576) + (ry.outer.inner*3)) + rx.outer.inner) + 567)]))
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
- kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ for (i1.inner: int32, 0, 4) {
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 16)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 20)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*196)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 24)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*4)) + i1.inner)]), 0f32)
}
}
}
@@ -999,7 +1233,7 @@ 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: 0.352 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.391 ms
</pre></div>
</div>
</div>
@@ -1029,36 +1263,36 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1077,14 +1311,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
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:
@@ -1102,430 +1336,619 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[72];
- __shared__ float kernel_shared[3072];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[28];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[16] = 0.000000e+00f;
+ conv2d_nchw[20] = 0.000000e+00f;
+ conv2d_nchw[24] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ conv2d_nchw[17] = 0.000000e+00f;
+ conv2d_nchw[21] = 0.000000e+00f;
+ conv2d_nchw[25] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[14] = 0.000000e+00f;
+ conv2d_nchw[18] = 0.000000e+00f;
+ conv2d_nchw[22] = 0.000000e+00f;
+ conv2d_nchw[26] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 18) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ conv2d_nchw[15] = 0.000000e+00f;
+ conv2d_nchw[19] = 0.000000e+00f;
+ conv2d_nchw[23] = 0.000000e+00f;
+ conv2d_nchw[27] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((9 <= ((((int)threadIdx.x) * 4) % 81)) && (((((int)threadIdx.x) * 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 4) / 81) * 49)) + ((((((int)threadIdx.x) * 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((9 <= (((((int)threadIdx.x) * 4) + 1) % 81)) && ((((((int)threadIdx.x) * 4) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((9 <= (((((int)threadIdx.x) * 4) + 2) % 81)) && ((((((int)threadIdx.x) * 4) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((9 <= (((((int)threadIdx.x) * 4) + 3) % 81)) && ((((((int)threadIdx.x) * 4) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 224)] = (((((9 <= (((((int)threadIdx.x) * 4) + 62) % 81)) && ((((((int)threadIdx.x) * 4) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 224) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 225)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 4) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 225) / 81) * 49)) + (((((((int)threadIdx.x) * 4) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 226)] = (((((9 <= (((((int)threadIdx.x) * 4) + 64) % 81)) && ((((((int)threadIdx.x) * 4) + 64) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 226) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 64) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 227)] = (((((9 <= (((((int)threadIdx.x) * 4) + 65) % 81)) && ((((((int)threadIdx.x) * 4) + 65) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 227) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 65) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 448)] = (((((9 <= (((((int)threadIdx.x) * 4) + 43) % 81)) && ((((((int)threadIdx.x) * 4) + 43) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 448) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 43) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 449)] = (((((9 <= (((((int)threadIdx.x) * 4) + 44) % 81)) && ((((((int)threadIdx.x) * 4) + 44) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 449) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 44) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 450)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 9) + 5) % 9)) && ((((((int)threadIdx.x) * 4) + 45) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 450) / 81) * 49)) + (((((((int)threadIdx.x) * 4) / 9) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 451)] = (((((9 <= (((((int)threadIdx.x) * 4) + 46) % 81)) && ((((((int)threadIdx.x) * 4) + 46) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 451) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 46) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 672)] = (((((9 <= (((((int)threadIdx.x) * 4) + 24) % 81)) && ((((((int)threadIdx.x) * 4) + 24) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 672) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 24) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 673)] = (((((9 <= (((((int)threadIdx.x) * 4) + 25) % 81)) && ((((((int)threadIdx.x) * 4) + 25) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 673) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 25) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 674)] = (((((9 <= (((((int)threadIdx.x) * 4) + 26) % 81)) && ((((((int)threadIdx.x) * 4) + 26) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 674) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 26) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 675)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 9) + 3) % 9)) && ((((((int)threadIdx.x) * 4) + 27) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 675) / 81) * 49)) + (((((((int)threadIdx.x) * 4) / 9) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 896)] = (((((9 <= (((((int)threadIdx.x) * 4) + 5) % 81)) && ((((((int)threadIdx.x) * 4) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 896) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 897)] = (((((9 <= (((((int)threadIdx.x) * 4) + 6) % 81)) && ((((((int)threadIdx.x) * 4) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 897) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 898)] = (((((9 <= (((((int)threadIdx.x) * 4) + 7) % 81)) && ((((((int)threadIdx.x) * 4) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 898) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 899)] = (((((9 <= (((((int)threadIdx.x) * 4) + 8) % 81)) && ((((((int)threadIdx.x) * 4) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 899) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1120)] = (((((9 <= (((((int)threadIdx.x) * 4) + 67) % 81)) && ((((((int)threadIdx.x) * 4) + 67) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1120) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 67) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1121)] = (((((9 <= (((((int)threadIdx.x) * 4) + 68) % 81)) && ((((((int)threadIdx.x) * 4) + 68) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1121) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 68) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1122)] = (((((9 <= (((((int)threadIdx.x) * 4) + 69) % 81)) && ((((((int)threadIdx.x) * 4) + 69) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1122) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 69) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 44) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1123)] = (((((9 <= (((((int)threadIdx.x) * 4) + 70) % 81)) && ((((((int)threadIdx.x) * 4) + 70) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 4) + 1123) / 81) * 49)) + (((((((int)threadIdx.x) * 4) + 70) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 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) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 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)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 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) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 64) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 3080)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3080) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3192)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3192) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 80) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3304)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3304) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 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)];
+ kernel_shared[(((int)threadIdx.x) + 3416)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3416) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3640)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3640) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 32) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3752)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3752) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3864)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3864) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 40) % 48) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3976)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3976) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 88) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 4088)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4088) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 56) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 112) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4200)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4200) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 24)];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 136) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 48)];
+ kernel_shared[(((int)threadIdx.x) + 4424)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4424) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ 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) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 4536)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4536) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 72)];
+ if (((int)threadIdx.x) < 16) {
+ kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4592) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 144)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 153)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 162)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 171)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 180)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 189)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 198)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 207)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 216)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 225)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 234)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 243)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 252)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 261)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 270)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 279)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 288)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 297)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 306)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 315)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 324)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 333)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 342)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 351)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 360)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 369)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 378)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 387)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 396)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 405)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 414)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 423)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 3)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 4)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 5)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 6)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 432)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 81)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 82)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 83)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 85)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 86)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 87)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 441)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 162)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 163)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 164)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 165)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 166)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 167)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 168)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 450)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 243)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 244)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 245)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 246)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 247)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 248)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 249)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 459)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 324)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 325)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 326)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 327)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 328)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 329)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 330)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 468)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 405)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 406)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 407)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 408)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 409)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 410)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 411)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 477)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 486)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 487)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 488)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 489)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 490)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 491)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 492)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 486)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 567)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 568)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 569)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 570)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 571)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 572)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 573)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 495)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 648)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 649)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 650)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 651)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 652)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 653)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 654)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 504)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 729)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 730)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 731)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 732)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 733)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 734)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 735)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 513)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 810)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 811)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 812)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 813)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 814)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 815)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 816)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 522)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 891)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 892)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 893)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 894)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 895)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 896)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 897)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 531)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 972)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 973)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 974)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 975)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 976)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 977)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 978)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 540)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1053)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1054)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1055)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1056)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1057)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1058)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1059)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 549)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1134)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1135)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1136)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1137)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1138)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1139)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1140)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 558)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1215)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1216)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1217)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1218)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1219)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1220)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
+ conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[((((ry_outer_inner * 9) + ((((int)threadIdx.x) % 7) * 9)) + rx_outer_inner) + 1221)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 576) + (ry_outer_inner * 3)) + rx_outer_inner) + 567)]));
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
- kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
- kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
- kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
- kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
- kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
- kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
- kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
- kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
- kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
- kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 16)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 20)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 196)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 24)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 4)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1562,7 +1985,7 @@ 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> ( 2 minutes 35.326 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 38.212 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 153dbd94d..aee74c8d4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ 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)
- 9.6971 9.7140 9.7200 9.6574 0.0282
+ 9.7472 9.7564 9.7623 9.7229 0.0173
</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 7b220c39c..1ca50c316 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ 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)
- 752.1354 752.4016 752.4102 751.5943 0.3826
+ 753.2252 753.4355 753.9080 752.3320 0.6604
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ 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 19.799 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.692 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 67d1814ac..b6005ce79 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,16 +620,15 @@ 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_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer: int32, 0, 4) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
- for (i1.outer: int32, 0, 16) {
- for (i.outer.inner: int32, 0, 2) {
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 16) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16))
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
{
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ 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
@@ -647,12 +646,12 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
- let cse_var_19: int32 = (((i0.outer*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
let cse_var_17: int32 = (cse_var_18 + 9)
let cse_var_16: int32 = (cse_var_18 + 8)
let cse_var_15: int32 = (cse_var_18 + 7)
@@ -690,11 +689,9 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
}
}
}
- for (i0.inner: int32, 0, 32) {
- for (i1.inner: int32, 0, 32) {
- let cse_var_22: int32 = ((((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32)) + i1.inner)
- compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
- }
+ for (i0.inner: int32, 0, 128) {
+ let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -732,7 +729,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.711 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.858 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 702f0b6a1..f15a06e8c 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:43.677</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.066</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,18 +331,18 @@
</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>00:43.635</p></td>
+<td><p>00:44.031</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>00:00.025</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><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>
-<td><p>00:00.008</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>
+<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>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 b5eadec71..d904295ad 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1167,8 +1167,8 @@ 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, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 97.00/97.00 result: MeasureResult(costs=(0.0023865407083333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8079521656036377, timestamp=1657667003.1451056) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 6 GFLOPS: 103.41/103.41 result: MeasureResult(costs=(0.0022385767083333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6624605655670166, timestamp=1657667899.0197847) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/103.41 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
@@ -1291,7 +1291,7 @@ 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, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/103.41 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
@@ -1414,7 +1414,7 @@ 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, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/103.41 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
@@ -1537,7 +1537,7 @@ 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, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/103.41 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
@@ -1555,7 +1555,7 @@ No: 10 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/103.41 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
@@ -1678,7 +1678,7 @@ 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, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/103.41 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
@@ -1801,7 +1801,7 @@ 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, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/103.41 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
@@ -1924,7 +1924,7 @@ 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, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/103.41 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
@@ -2047,7 +2047,7 @@ 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, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/103.41 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
@@ -2170,7 +2170,7 @@ 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, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/103.41 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
@@ -2293,7 +2293,7 @@ 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, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/103.41 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
@@ -2416,7 +2416,7 @@ 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, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/103.41 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
@@ -2539,7 +2539,7 @@ 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, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/97.00 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/103.41 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2627,7 +2627,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fdc40c70fa2
+ 12: 0x00007f2f78db2fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2692,7 +2692,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 144.73/144.73 result: MeasureResult(costs=(0.00159954444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4048492908477783, timestamp=1657667029.568814) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 144.13/144.13 result: MeasureResult(costs=(0.00160622003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4498698711395264, timestamp=1657667925.618543) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2733,7 +2733,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
-Time cost of this operator: 0.001962
+Time cost of this operator: 0.001984
</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 f6fa0dee2..010b9c6b3 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ 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 310.2 98.713 (1, 2, 10, 10, 3) 2 1 [310.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.981 (1, 6, 10, 10) 1 1 [3.082]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.961 0.306 (1, 1, 10, 10, 3) 1 1 [0.961]
-Total_time - 314.243 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.9 98.73 (1, 2, 10, 10, 3) 2 1 [308.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.018 0.965 (1, 6, 10, 10) 1 1 [3.018]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.306 (1, 1, 10, 10, 3) 1 1 [0.956]
+Total_time - 312.874 - - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ 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 80.5 96.713 (1, 6, 10, 10, 1) 2 1 [80.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 2.126 (1, 6, 10, 10) 1 1 [1.77]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.161 (1, 1, 10, 10, 3) 1 1 [0.967]
-Total_time - 83.236 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 87.688 96.439 (1, 6, 10, 10, 1) 2 1 [87.688]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.281 2.508 (1, 6, 10, 10) 1 1 [2.281]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.957 1.052 (1, 1, 10, 10, 3) 1 1 [0.957]
+Total_time - 90.925 - - - - -
</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 31db95cd4..aaf57c2eb 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ 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/tmpfy2jac6e/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpaisq2qu8/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ 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/tmpfy2jac6e/images/target contains 8144 images
-/tmp/tmpfy2jac6e/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/tmpaisq2qu8/images/target contains 8144 images
+/tmp/tmpaisq2qu8/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ 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: 0.2115 - accuracy: 0.9239 - val_loss: 0.1373 - val_accuracy: 0.9539
+328/328 - 55s - loss: 0.2160 - accuracy: 0.9263 - val_loss: 0.2027 - val_accuracy: 0.9486
Epoch 2/3
-328/328 - 52s - loss: 0.1027 - accuracy: 0.9617 - val_loss: 0.1240 - val_accuracy: 0.9615
+328/328 - 52s - loss: 0.0984 - accuracy: 0.9627 - val_loss: 0.1408 - val_accuracy: 0.9626
Epoch 3/3
-328/328 - 52s - loss: 0.0644 - accuracy: 0.9762 - val_loss: 0.1382 - val_accuracy: 0.9603
+328/328 - 52s - loss: 0.0644 - accuracy: 0.9771 - val_loss: 0.1682 - val_accuracy: 0.9596
-<keras.callbacks.History object at 0x7f8a95194750>
+<keras.callbacks.History object at 0x7f8a01075cd0>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ 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> ( 4 minutes 43.425 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 56.932 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 67e57805f..d9d29c58d 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>05:30.471</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:43.790</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:43.425</p></td>
+<td><p>04:56.932</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>00:43.813</p></td>
+<td><p>00:43.266</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:03.231</p></td>
+<td><p>00:03.589</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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 d5bc667f4..3a84935f7 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:11.190</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.319</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.751</p></td>
+<td><p>00:09.790</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:01.434</p></td>
+<td><p>00:01.522</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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 88ac9669c..e4d8be27b 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -517,7 +517,7 @@ 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 0x7f8a19d87b90>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f892fa1b290>
</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 11e1aba98..11714f096 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:03.957</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.077</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.825</p></td>
+<td><p>00:01.904</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>00:00.948</p></td>
+<td><p>00:00.956</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>00:00.510</p></td>
+<td><p>00:00.525</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>00:00.500</p></td>
+<td><p>00:00.512</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>00:00.098</p></td>
+<td><p>00:00.103</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.035</p></td>
+<td><p>00:00.036</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
@@ -359,7 +359,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.013</p></td>
+<td><p>00:00.014</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 1d8a1dbee..7e0b827fe 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -572,7 +572,7 @@ 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/tmp35s4lpxn/input0.cc'\nsource_filename = \"/tmp/tmp35s4lpxn/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/tmpidqrvcss/input0.cc'\nsource_filename = \"/tmp/tmpidqrvcss/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 8d059571c..97110a1e0 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ 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>
@@ -1881,7 +1881,7 @@ 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 ff1a264dd..6e4a783e7 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/d07f2fb80/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/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/d07f2fb80/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/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/d07f2fb80/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/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/d07f2fb80/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/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/d07f2fb80/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/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/d07f2fb80/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/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 deb1be30c..612d30a18 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/d07f2fb80/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L223">memory.ts:223</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">temp<wbr>Args<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L208">memory.ts:208</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -194,7 +194,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L312">memory.ts:312</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L284">memory.ts:284</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L388">memory.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -300,7 +300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L376">memory.ts:376</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -340,7 +340,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L267">memory.ts:267</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -373,7 +373,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L243">memory.ts:243</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -390,7 +390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L321">memory.ts:321</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -422,7 +422,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L252">memory.ts:252</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -444,7 +444,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L359">memory.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -470,7 +470,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L342">memory.ts:342</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -496,7 +496,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L350">memory.ts:350</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -522,7 +522,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L326">memory.ts:326</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -548,7 +548,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L363">memory.ts:363</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L346">memory.ts:346</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index f4afda089..d621c91a9 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 8ef8c41d6..a22b1d284 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 019ab340b..567b1b20a 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L86">environment.ts:86</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<aside class="tsd-sources">
<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L70">environment.ts:70</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L69">environment.ts:69</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L78">environment.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L84">environment.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index bb1a0786d..6e1cc1a7d 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index aef785b39..d2869a13e 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 7ff54a1fb..192843e33 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 100e9675c..e6c180d47 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 2b5c01477..cb9f66b91 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 5cf857fa2..14d26d5b6 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 252839a2d..588d06a99 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 2f01a1fef..886335287 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index f1ff95de5..c96e76858 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index ac6cdd1b2..9d4985358 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 80e28c580..1946c8486 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</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/d07f2fb80/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 9ff04059d..06067c70c 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 7bdbabc12..967a877a1 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</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/d07f2fb80/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 38eb6592d..688f4123b 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 3ea8a6418..3907360fa 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 817955299..61591d4d7 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 70bd64a49..64dd9c759 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index b47a3b8ea..4a5676502 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index ac9db04e1..e1b24b0fe 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/d07f2fb80/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/1d5d357d6/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 080159b42..368bfe401 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 27e21897d..93db02d5b 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.482</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.281</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.476</p></td>
+<td><p>00:21.274</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 5d3b2cb94..88a9d05ff 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
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 22.13s!
+resnet18_v1 inference graph built in 23.11s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 530a1f1f6..bb031dac3 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"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 15.54s!
+yolov3-tiny inference graph built in 16.18s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index e125b2a5e..3d4281c63 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:30.1000</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:32.468</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.395</p></td>
+<td><p>00:48.832</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:42.604</p></td>
+<td><p>00:43.636</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index df5707256..79d58c7b7 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.227</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.255</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
... 670 lines suppressed ...